Upload folder using huggingface_hub
Browse files- config.json +45 -0
- configuration_internlm3.py +197 -0
- generation_config.json +9 -0
- inputs_stats.pth +3 -0
- outputs_stats.pth +3 -0
- pytorch_model-00001-of-00004.bin +3 -0
- pytorch_model-00002-of-00004.bin +3 -0
- pytorch_model-00003-of-00004.bin +3 -0
- pytorch_model-00004-of-00004.bin +3 -0
- pytorch_model.bin.index.json +1114 -0
- special_tokens_map.json +54 -0
- tokenization_internlm3.py +294 -0
- tokenizer.model +3 -0
- tokenizer_config.json +249 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/141/develop_internlm3_open_source_hf_0110v1/20250109095225_hf-080_open_source_hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"InternLM3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_internlm3.InternLM3Config",
|
| 9 |
+
"AutoModel": "modeling_internlm3.InternLM3Model",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_internlm3.InternLM3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bias": false,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 4096,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 10240,
|
| 20 |
+
"max_position_embeddings": 32768,
|
| 21 |
+
"model_type": "internlm3",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 48,
|
| 24 |
+
"num_key_value_heads": 2,
|
| 25 |
+
"pad_token_id": 2,
|
| 26 |
+
"qkv_bias": false,
|
| 27 |
+
"quantization_config": {
|
| 28 |
+
"bits": 4,
|
| 29 |
+
"group_size": 128,
|
| 30 |
+
"quant_method": "awq",
|
| 31 |
+
"version": "gemm",
|
| 32 |
+
"zero_point": true
|
| 33 |
+
},
|
| 34 |
+
"rms_norm_eps": 1e-05,
|
| 35 |
+
"rope_scaling": {
|
| 36 |
+
"factor": 6.0,
|
| 37 |
+
"rope_type": "dynamic"
|
| 38 |
+
},
|
| 39 |
+
"rope_theta": 50000000,
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"torch_dtype": "float16",
|
| 42 |
+
"transformers_version": "4.47.0",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"vocab_size": 128512
|
| 45 |
+
}
|
configuration_internlm3.py
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# coding=utf-8
|
| 2 |
+
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
|
| 3 |
+
#
|
| 4 |
+
# This code is based on transformers/src/transformers/models/llama/configuration_llama.py
|
| 5 |
+
#
|
| 6 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 7 |
+
# you may not use this file except in compliance with the License.
|
| 8 |
+
# You may obtain a copy of the License at
|
| 9 |
+
#
|
| 10 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 11 |
+
#
|
| 12 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 13 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 14 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 15 |
+
# See the License for the specific language governing permissions and
|
| 16 |
+
# limitations under the License.
|
| 17 |
+
""" InternLM3 model configuration"""
|
| 18 |
+
|
| 19 |
+
from transformers.configuration_utils import PretrainedConfig
|
| 20 |
+
from transformers.modeling_rope_utils import rope_config_validation
|
| 21 |
+
from transformers.utils import logging
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
logger = logging.get_logger(__name__)
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
class InternLM3Config(PretrainedConfig):
|
| 28 |
+
r"""
|
| 29 |
+
This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate
|
| 30 |
+
an InternLM2 model according to the specified arguments, defining the model architecture. Instantiating a
|
| 31 |
+
configuration with the defaults will yield a similar configuration to that of the InternLM2-7B.
|
| 32 |
+
|
| 33 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
| 34 |
+
documentation from [`PretrainedConfig`] for more information.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
Args:
|
| 38 |
+
vocab_size (`int`, *optional*, defaults to 151936):
|
| 39 |
+
Vocabulary size of the InternLM3 model. Defines the number of different tokens that can be represented by the
|
| 40 |
+
`inputs_ids` passed when calling [`InternLM3Model`]
|
| 41 |
+
hidden_size (`int`, *optional*, defaults to 4096):
|
| 42 |
+
Dimension of the hidden representations.
|
| 43 |
+
intermediate_size (`int`, *optional*, defaults to 22016):
|
| 44 |
+
Dimension of the MLP representations.
|
| 45 |
+
num_hidden_layers (`int`, *optional*, defaults to 32):
|
| 46 |
+
Number of hidden layers in the Transformer encoder.
|
| 47 |
+
num_attention_heads (`int`, *optional*, defaults to 32):
|
| 48 |
+
Number of attention heads for each attention layer in the Transformer encoder.
|
| 49 |
+
num_key_value_heads (`int`, *optional*, defaults to 32):
|
| 50 |
+
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
|
| 51 |
+
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
|
| 52 |
+
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
|
| 53 |
+
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
|
| 54 |
+
by meanpooling all the original heads within that group. For more details checkout [this
|
| 55 |
+
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
|
| 56 |
+
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
|
| 57 |
+
The non-linear activation function (function or string) in the decoder.
|
| 58 |
+
max_position_embeddings (`int`, *optional*, defaults to 32768):
|
| 59 |
+
The maximum sequence length that this model might ever be used with.
|
| 60 |
+
initializer_range (`float`, *optional*, defaults to 0.02):
|
| 61 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
| 62 |
+
rms_norm_eps (`float`, *optional*, defaults to 1e-06):
|
| 63 |
+
The epsilon used by the rms normalization layers.
|
| 64 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
| 65 |
+
Whether or not the model should return the last key/values attentions (not used by all models). Only
|
| 66 |
+
relevant if `config.is_decoder=True`.
|
| 67 |
+
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
|
| 68 |
+
Whether the model's input and output word embeddings should be tied.
|
| 69 |
+
rope_theta (`float`, *optional*, defaults to 10000.0):
|
| 70 |
+
The base period of the RoPE embeddings.
|
| 71 |
+
rope_scaling (`Dict`, *optional*):
|
| 72 |
+
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
|
| 73 |
+
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
|
| 74 |
+
accordingly.
|
| 75 |
+
Expected contents:
|
| 76 |
+
`rope_type` (`str`):
|
| 77 |
+
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
|
| 78 |
+
'llama3'], with 'default' being the original RoPE implementation.
|
| 79 |
+
`factor` (`float`, *optional*):
|
| 80 |
+
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
|
| 81 |
+
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
|
| 82 |
+
original maximum pre-trained length.
|
| 83 |
+
`original_max_position_embeddings` (`int`, *optional*):
|
| 84 |
+
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
|
| 85 |
+
pretraining.
|
| 86 |
+
`attention_factor` (`float`, *optional*):
|
| 87 |
+
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
|
| 88 |
+
computation. If unspecified, it defaults to value recommended by the implementation, using the
|
| 89 |
+
`factor` field to infer the suggested value.
|
| 90 |
+
`beta_fast` (`float`, *optional*):
|
| 91 |
+
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
|
| 92 |
+
ramp function. If unspecified, it defaults to 32.
|
| 93 |
+
`beta_slow` (`float`, *optional*):
|
| 94 |
+
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
|
| 95 |
+
ramp function. If unspecified, it defaults to 1.
|
| 96 |
+
`short_factor` (`List[float]`, *optional*):
|
| 97 |
+
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
|
| 98 |
+
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
| 99 |
+
size divided by the number of attention heads divided by 2
|
| 100 |
+
`long_factor` (`List[float]`, *optional*):
|
| 101 |
+
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
|
| 102 |
+
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
| 103 |
+
size divided by the number of attention heads divided by 2
|
| 104 |
+
`low_freq_factor` (`float`, *optional*):
|
| 105 |
+
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
|
| 106 |
+
`high_freq_factor` (`float`, *optional*):
|
| 107 |
+
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
|
| 108 |
+
qkv_bias (`bool`, *optional*, defaults to `False`):
|
| 109 |
+
Whether to use a bias in the query, key and value projection layers during self-attention.
|
| 110 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
| 111 |
+
The dropout ratio for the attention probabilities.
|
| 112 |
+
bias (`bool`, *optional*, defaults to `False`):
|
| 113 |
+
Whether to use a bias in o_proj, up_proj, down_proj and gate_proj layers.
|
| 114 |
+
head_dim (`int`, *optional*):
|
| 115 |
+
The attention head dimension. If None, it will default to hidden_size // num_heads
|
| 116 |
+
|
| 117 |
+
```python
|
| 118 |
+
>>> from transformers import InternLM3Model, InternLM3Config
|
| 119 |
+
|
| 120 |
+
>>> # Initializing a InternLM3 style configuration
|
| 121 |
+
>>> configuration = InternLM3Config()
|
| 122 |
+
|
| 123 |
+
>>> # Initializing a model from the InternLM3-8B style configuration
|
| 124 |
+
>>> model = InternLM3Model(configuration)
|
| 125 |
+
|
| 126 |
+
>>> # Accessing the model configuration
|
| 127 |
+
>>> configuration = model.config
|
| 128 |
+
```"""
|
| 129 |
+
|
| 130 |
+
model_type = "internlm3"
|
| 131 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 132 |
+
|
| 133 |
+
# Default tensor parallel plan for base model `InternLM3`
|
| 134 |
+
base_model_tp_plan = {
|
| 135 |
+
"layers.*.self_attn.q_proj": "colwise",
|
| 136 |
+
"layers.*.self_attn.k_proj": "colwise",
|
| 137 |
+
"layers.*.self_attn.v_proj": "colwise",
|
| 138 |
+
"layers.*.self_attn.o_proj": "rowwise",
|
| 139 |
+
"layers.*.mlp.gate_proj": "colwise",
|
| 140 |
+
"layers.*.mlp.up_proj": "colwise",
|
| 141 |
+
"layers.*.mlp.down_proj": "rowwise",
|
| 142 |
+
}
|
| 143 |
+
|
| 144 |
+
def __init__(
|
| 145 |
+
self,
|
| 146 |
+
vocab_size=128512,
|
| 147 |
+
hidden_size=4096,
|
| 148 |
+
intermediate_size=11008,
|
| 149 |
+
num_hidden_layers=32,
|
| 150 |
+
num_attention_heads=32,
|
| 151 |
+
num_key_value_heads=32,
|
| 152 |
+
hidden_act="silu",
|
| 153 |
+
max_position_embeddings=32768,
|
| 154 |
+
initializer_range=0.02,
|
| 155 |
+
rms_norm_eps=1e-6,
|
| 156 |
+
use_cache=True,
|
| 157 |
+
tie_word_embeddings=False,
|
| 158 |
+
rope_theta=10000.0,
|
| 159 |
+
rope_scaling=None,
|
| 160 |
+
qkv_bias=False,
|
| 161 |
+
attention_dropout=0.0,
|
| 162 |
+
bias=False,
|
| 163 |
+
head_dim=None,
|
| 164 |
+
**kwargs,
|
| 165 |
+
):
|
| 166 |
+
self.vocab_size = vocab_size
|
| 167 |
+
self.max_position_embeddings = max_position_embeddings
|
| 168 |
+
self.hidden_size = hidden_size
|
| 169 |
+
self.intermediate_size = intermediate_size
|
| 170 |
+
self.num_hidden_layers = num_hidden_layers
|
| 171 |
+
self.num_attention_heads = num_attention_heads
|
| 172 |
+
|
| 173 |
+
# for backward compatibility
|
| 174 |
+
if num_key_value_heads is None:
|
| 175 |
+
num_key_value_heads = num_attention_heads
|
| 176 |
+
|
| 177 |
+
self.num_key_value_heads = num_key_value_heads
|
| 178 |
+
self.hidden_act = hidden_act
|
| 179 |
+
self.initializer_range = initializer_range
|
| 180 |
+
self.rms_norm_eps = rms_norm_eps
|
| 181 |
+
self.use_cache = use_cache
|
| 182 |
+
self.rope_theta = rope_theta
|
| 183 |
+
self.rope_scaling = rope_scaling
|
| 184 |
+
self.qkv_bias = qkv_bias
|
| 185 |
+
self.attention_dropout = attention_dropout
|
| 186 |
+
self.bias = bias
|
| 187 |
+
self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
|
| 188 |
+
# Validate the correctness of rotary position embeddings parameters
|
| 189 |
+
# BC: if there is a 'type' field, move it to 'rope_type'.
|
| 190 |
+
if self.rope_scaling is not None and "type" in self.rope_scaling:
|
| 191 |
+
self.rope_scaling["rope_type"] = self.rope_scaling["type"]
|
| 192 |
+
rope_config_validation(self)
|
| 193 |
+
|
| 194 |
+
super().__init__(
|
| 195 |
+
tie_word_embeddings=tie_word_embeddings,
|
| 196 |
+
**kwargs,
|
| 197 |
+
)
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
2,
|
| 5 |
+
128131
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "4.47.0"
|
| 9 |
+
}
|
inputs_stats.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7853a5b742157d7be77086c0f9b5a2792812110bc3583b3d1792e5d6b3f152b
|
| 3 |
+
size 17184926
|
outputs_stats.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17dd70fe4bc9e0ae845a7e4da821da8bc8a37c17953e230c071d443874fbdafb
|
| 3 |
+
size 20560683
|
pytorch_model-00001-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:099d2f8d86279b47869d1786192f1c4216807a88d3de994682bf28bb23d2b38e
|
| 3 |
+
size 1994399684
|
pytorch_model-00002-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9a4089782db1d1b610acdb071bc1f73eafa171a38ae6e7dffcd7cedef8c526c
|
| 3 |
+
size 1995516698
|
pytorch_model-00003-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:511eab2c579e16436dbf44fda740bf9d46783859e18d3c87e12031c4eb36a2b2
|
| 3 |
+
size 1090948490
|
pytorch_model-00004-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a87c44deb71fa9f68dfd765f720df88f23803eb2c1f7ebed7b55a963e3635447
|
| 3 |
+
size 1052771717
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,1114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6133260288
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"model.layers.0.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"model.layers.0.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"model.layers.0.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"model.layers.0.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"model.layers.0.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"model.layers.0.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"model.layers.0.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"model.layers.0.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"model.layers.0.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"model.layers.0.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"model.layers.0.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"model.layers.0.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"model.layers.0.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"model.layers.0.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"model.layers.0.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"model.layers.0.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"model.layers.0.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"model.layers.1.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 33 |
+
"model.layers.1.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 34 |
+
"model.layers.1.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 35 |
+
"model.layers.1.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 36 |
+
"model.layers.1.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 37 |
+
"model.layers.1.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 38 |
+
"model.layers.1.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 39 |
+
"model.layers.1.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 40 |
+
"model.layers.1.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 41 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 42 |
+
"model.layers.1.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 43 |
+
"model.layers.1.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 44 |
+
"model.layers.1.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 45 |
+
"model.layers.1.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 46 |
+
"model.layers.1.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 47 |
+
"model.layers.1.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 48 |
+
"model.layers.1.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 49 |
+
"model.layers.1.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 50 |
+
"model.layers.1.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 51 |
+
"model.layers.1.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 52 |
+
"model.layers.1.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 53 |
+
"model.layers.1.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 54 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 55 |
+
"model.layers.10.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 56 |
+
"model.layers.10.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 57 |
+
"model.layers.10.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 58 |
+
"model.layers.10.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 59 |
+
"model.layers.10.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 60 |
+
"model.layers.10.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 61 |
+
"model.layers.10.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 62 |
+
"model.layers.10.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 63 |
+
"model.layers.10.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 64 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 65 |
+
"model.layers.10.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 66 |
+
"model.layers.10.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 67 |
+
"model.layers.10.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 68 |
+
"model.layers.10.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 69 |
+
"model.layers.10.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 70 |
+
"model.layers.10.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 71 |
+
"model.layers.10.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 72 |
+
"model.layers.10.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 73 |
+
"model.layers.10.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 74 |
+
"model.layers.10.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 75 |
+
"model.layers.10.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 76 |
+
"model.layers.10.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 77 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"model.layers.11.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"model.layers.11.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"model.layers.11.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"model.layers.11.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"model.layers.11.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"model.layers.11.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"model.layers.11.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"model.layers.11.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"model.layers.11.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"model.layers.11.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 89 |
+
"model.layers.11.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 90 |
+
"model.layers.11.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 91 |
+
"model.layers.11.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 92 |
+
"model.layers.11.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 93 |
+
"model.layers.11.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 94 |
+
"model.layers.11.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 95 |
+
"model.layers.11.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 96 |
+
"model.layers.11.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 97 |
+
"model.layers.11.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 98 |
+
"model.layers.11.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 99 |
+
"model.layers.11.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 100 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"model.layers.12.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"model.layers.12.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"model.layers.12.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"model.layers.12.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"model.layers.12.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"model.layers.12.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"model.layers.12.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"model.layers.12.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"model.layers.12.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"model.layers.12.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"model.layers.12.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"model.layers.12.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"model.layers.12.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"model.layers.12.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"model.layers.12.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"model.layers.12.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"model.layers.12.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"model.layers.12.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"model.layers.12.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"model.layers.12.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"model.layers.12.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"model.layers.13.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"model.layers.13.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"model.layers.13.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"model.layers.13.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"model.layers.13.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 129 |
+
"model.layers.13.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 130 |
+
"model.layers.13.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"model.layers.13.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 132 |
+
"model.layers.13.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 133 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"model.layers.13.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"model.layers.13.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"model.layers.13.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"model.layers.13.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"model.layers.13.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"model.layers.13.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"model.layers.13.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 141 |
+
"model.layers.13.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 142 |
+
"model.layers.13.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 143 |
+
"model.layers.13.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 144 |
+
"model.layers.13.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 145 |
+
"model.layers.13.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 146 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 147 |
+
"model.layers.14.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 148 |
+
"model.layers.14.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 149 |
+
"model.layers.14.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 150 |
+
"model.layers.14.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 151 |
+
"model.layers.14.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 152 |
+
"model.layers.14.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 153 |
+
"model.layers.14.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 154 |
+
"model.layers.14.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 155 |
+
"model.layers.14.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 156 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 157 |
+
"model.layers.14.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 158 |
+
"model.layers.14.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 159 |
+
"model.layers.14.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 160 |
+
"model.layers.14.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 161 |
+
"model.layers.14.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 162 |
+
"model.layers.14.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 163 |
+
"model.layers.14.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 164 |
+
"model.layers.14.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 165 |
+
"model.layers.14.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 166 |
+
"model.layers.14.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 167 |
+
"model.layers.14.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 168 |
+
"model.layers.14.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 169 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 170 |
+
"model.layers.15.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 171 |
+
"model.layers.15.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 172 |
+
"model.layers.15.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 173 |
+
"model.layers.15.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 174 |
+
"model.layers.15.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 175 |
+
"model.layers.15.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 176 |
+
"model.layers.15.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 177 |
+
"model.layers.15.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 178 |
+
"model.layers.15.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 179 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 180 |
+
"model.layers.15.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 181 |
+
"model.layers.15.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 182 |
+
"model.layers.15.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 183 |
+
"model.layers.15.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 184 |
+
"model.layers.15.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 185 |
+
"model.layers.15.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 186 |
+
"model.layers.15.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 187 |
+
"model.layers.15.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 188 |
+
"model.layers.15.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 189 |
+
"model.layers.15.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 190 |
+
"model.layers.15.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 191 |
+
"model.layers.15.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 192 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 193 |
+
"model.layers.16.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 194 |
+
"model.layers.16.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 195 |
+
"model.layers.16.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 196 |
+
"model.layers.16.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 197 |
+
"model.layers.16.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 198 |
+
"model.layers.16.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 199 |
+
"model.layers.16.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 200 |
+
"model.layers.16.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 201 |
+
"model.layers.16.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 202 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 203 |
+
"model.layers.16.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 204 |
+
"model.layers.16.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 205 |
+
"model.layers.16.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 206 |
+
"model.layers.16.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 207 |
+
"model.layers.16.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 208 |
+
"model.layers.16.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 209 |
+
"model.layers.16.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 210 |
+
"model.layers.16.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 211 |
+
"model.layers.16.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 212 |
+
"model.layers.16.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 213 |
+
"model.layers.16.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 214 |
+
"model.layers.16.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 215 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 216 |
+
"model.layers.17.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 217 |
+
"model.layers.17.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 218 |
+
"model.layers.17.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 219 |
+
"model.layers.17.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 220 |
+
"model.layers.17.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 221 |
+
"model.layers.17.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 222 |
+
"model.layers.17.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 223 |
+
"model.layers.17.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 224 |
+
"model.layers.17.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 225 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 226 |
+
"model.layers.17.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 227 |
+
"model.layers.17.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 228 |
+
"model.layers.17.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 229 |
+
"model.layers.17.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 230 |
+
"model.layers.17.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 231 |
+
"model.layers.17.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 232 |
+
"model.layers.17.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 233 |
+
"model.layers.17.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 234 |
+
"model.layers.17.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 235 |
+
"model.layers.17.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 236 |
+
"model.layers.17.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 237 |
+
"model.layers.17.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 238 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 239 |
+
"model.layers.18.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 240 |
+
"model.layers.18.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 241 |
+
"model.layers.18.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 242 |
+
"model.layers.18.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 243 |
+
"model.layers.18.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 244 |
+
"model.layers.18.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 245 |
+
"model.layers.18.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 246 |
+
"model.layers.18.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 247 |
+
"model.layers.18.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 248 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 249 |
+
"model.layers.18.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 250 |
+
"model.layers.18.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 251 |
+
"model.layers.18.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 252 |
+
"model.layers.18.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 253 |
+
"model.layers.18.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 254 |
+
"model.layers.18.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 255 |
+
"model.layers.18.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 256 |
+
"model.layers.18.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 257 |
+
"model.layers.18.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 258 |
+
"model.layers.18.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 259 |
+
"model.layers.18.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 260 |
+
"model.layers.18.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 261 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 262 |
+
"model.layers.19.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 263 |
+
"model.layers.19.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 264 |
+
"model.layers.19.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 265 |
+
"model.layers.19.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 266 |
+
"model.layers.19.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 267 |
+
"model.layers.19.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 268 |
+
"model.layers.19.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 269 |
+
"model.layers.19.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 270 |
+
"model.layers.19.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 271 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 272 |
+
"model.layers.19.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 273 |
+
"model.layers.19.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 274 |
+
"model.layers.19.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 275 |
+
"model.layers.19.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 276 |
+
"model.layers.19.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 277 |
+
"model.layers.19.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 278 |
+
"model.layers.19.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 279 |
+
"model.layers.19.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 280 |
+
"model.layers.19.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 281 |
+
"model.layers.19.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 282 |
+
"model.layers.19.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 283 |
+
"model.layers.19.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 284 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 285 |
+
"model.layers.2.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 286 |
+
"model.layers.2.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 287 |
+
"model.layers.2.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 288 |
+
"model.layers.2.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 289 |
+
"model.layers.2.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 290 |
+
"model.layers.2.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 291 |
+
"model.layers.2.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 292 |
+
"model.layers.2.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 293 |
+
"model.layers.2.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 294 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 295 |
+
"model.layers.2.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 296 |
+
"model.layers.2.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 297 |
+
"model.layers.2.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 298 |
+
"model.layers.2.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 299 |
+
"model.layers.2.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 300 |
+
"model.layers.2.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 301 |
+
"model.layers.2.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 302 |
+
"model.layers.2.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 303 |
+
"model.layers.2.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 304 |
+
"model.layers.2.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 305 |
+
"model.layers.2.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 306 |
+
"model.layers.2.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 307 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 308 |
+
"model.layers.20.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 309 |
+
"model.layers.20.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 310 |
+
"model.layers.20.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 311 |
+
"model.layers.20.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 312 |
+
"model.layers.20.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 313 |
+
"model.layers.20.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 314 |
+
"model.layers.20.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 315 |
+
"model.layers.20.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 316 |
+
"model.layers.20.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 317 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 318 |
+
"model.layers.20.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 319 |
+
"model.layers.20.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 320 |
+
"model.layers.20.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 321 |
+
"model.layers.20.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 322 |
+
"model.layers.20.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 323 |
+
"model.layers.20.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 324 |
+
"model.layers.20.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 325 |
+
"model.layers.20.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 326 |
+
"model.layers.20.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 327 |
+
"model.layers.20.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 328 |
+
"model.layers.20.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 329 |
+
"model.layers.20.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 330 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 331 |
+
"model.layers.21.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 332 |
+
"model.layers.21.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 333 |
+
"model.layers.21.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 334 |
+
"model.layers.21.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 335 |
+
"model.layers.21.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 336 |
+
"model.layers.21.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 337 |
+
"model.layers.21.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 338 |
+
"model.layers.21.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 339 |
+
"model.layers.21.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 340 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 341 |
+
"model.layers.21.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 342 |
+
"model.layers.21.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 343 |
+
"model.layers.21.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 344 |
+
"model.layers.21.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 345 |
+
"model.layers.21.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 346 |
+
"model.layers.21.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 347 |
+
"model.layers.21.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 348 |
+
"model.layers.21.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 349 |
+
"model.layers.21.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 350 |
+
"model.layers.21.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 351 |
+
"model.layers.21.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 352 |
+
"model.layers.21.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 353 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 354 |
+
"model.layers.22.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 355 |
+
"model.layers.22.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 356 |
+
"model.layers.22.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 357 |
+
"model.layers.22.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 358 |
+
"model.layers.22.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 359 |
+
"model.layers.22.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 360 |
+
"model.layers.22.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 361 |
+
"model.layers.22.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 362 |
+
"model.layers.22.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 363 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 364 |
+
"model.layers.22.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 365 |
+
"model.layers.22.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 366 |
+
"model.layers.22.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 367 |
+
"model.layers.22.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 368 |
+
"model.layers.22.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 369 |
+
"model.layers.22.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 370 |
+
"model.layers.22.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 371 |
+
"model.layers.22.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 372 |
+
"model.layers.22.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 373 |
+
"model.layers.22.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 374 |
+
"model.layers.22.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 375 |
+
"model.layers.22.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 376 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 377 |
+
"model.layers.23.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 378 |
+
"model.layers.23.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 379 |
+
"model.layers.23.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 380 |
+
"model.layers.23.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 381 |
+
"model.layers.23.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 382 |
+
"model.layers.23.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 383 |
+
"model.layers.23.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 384 |
+
"model.layers.23.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 385 |
+
"model.layers.23.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 386 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 387 |
+
"model.layers.23.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 388 |
+
"model.layers.23.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 389 |
+
"model.layers.23.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 390 |
+
"model.layers.23.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 391 |
+
"model.layers.23.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 392 |
+
"model.layers.23.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 393 |
+
"model.layers.23.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 394 |
+
"model.layers.23.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 395 |
+
"model.layers.23.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 396 |
+
"model.layers.23.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 397 |
+
"model.layers.23.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 398 |
+
"model.layers.23.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 399 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 400 |
+
"model.layers.24.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 401 |
+
"model.layers.24.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 402 |
+
"model.layers.24.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 403 |
+
"model.layers.24.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 404 |
+
"model.layers.24.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 405 |
+
"model.layers.24.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 406 |
+
"model.layers.24.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 407 |
+
"model.layers.24.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 408 |
+
"model.layers.24.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 409 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 410 |
+
"model.layers.24.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 411 |
+
"model.layers.24.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 412 |
+
"model.layers.24.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 413 |
+
"model.layers.24.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 414 |
+
"model.layers.24.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 415 |
+
"model.layers.24.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 416 |
+
"model.layers.24.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 417 |
+
"model.layers.24.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 418 |
+
"model.layers.24.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 419 |
+
"model.layers.24.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 420 |
+
"model.layers.24.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 421 |
+
"model.layers.24.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 422 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 423 |
+
"model.layers.25.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 424 |
+
"model.layers.25.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 425 |
+
"model.layers.25.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 426 |
+
"model.layers.25.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 427 |
+
"model.layers.25.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 428 |
+
"model.layers.25.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 429 |
+
"model.layers.25.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 430 |
+
"model.layers.25.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 431 |
+
"model.layers.25.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 432 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 433 |
+
"model.layers.25.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 434 |
+
"model.layers.25.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 435 |
+
"model.layers.25.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 436 |
+
"model.layers.25.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 437 |
+
"model.layers.25.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 438 |
+
"model.layers.25.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 439 |
+
"model.layers.25.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 440 |
+
"model.layers.25.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 441 |
+
"model.layers.25.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 442 |
+
"model.layers.25.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 443 |
+
"model.layers.25.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 444 |
+
"model.layers.25.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 445 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 446 |
+
"model.layers.26.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 447 |
+
"model.layers.26.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 448 |
+
"model.layers.26.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 449 |
+
"model.layers.26.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 450 |
+
"model.layers.26.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 451 |
+
"model.layers.26.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 452 |
+
"model.layers.26.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 453 |
+
"model.layers.26.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 454 |
+
"model.layers.26.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 455 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 456 |
+
"model.layers.26.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 457 |
+
"model.layers.26.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 458 |
+
"model.layers.26.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 459 |
+
"model.layers.26.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 460 |
+
"model.layers.26.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 461 |
+
"model.layers.26.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 462 |
+
"model.layers.26.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 463 |
+
"model.layers.26.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 464 |
+
"model.layers.26.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 465 |
+
"model.layers.26.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 466 |
+
"model.layers.26.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 467 |
+
"model.layers.26.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 468 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 469 |
+
"model.layers.27.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 470 |
+
"model.layers.27.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 471 |
+
"model.layers.27.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 472 |
+
"model.layers.27.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 473 |
+
"model.layers.27.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 474 |
+
"model.layers.27.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 475 |
+
"model.layers.27.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 476 |
+
"model.layers.27.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 477 |
+
"model.layers.27.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 478 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 479 |
+
"model.layers.27.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 480 |
+
"model.layers.27.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 481 |
+
"model.layers.27.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 482 |
+
"model.layers.27.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 483 |
+
"model.layers.27.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 484 |
+
"model.layers.27.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 485 |
+
"model.layers.27.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 486 |
+
"model.layers.27.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 487 |
+
"model.layers.27.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 488 |
+
"model.layers.27.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 489 |
+
"model.layers.27.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 490 |
+
"model.layers.27.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 491 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 492 |
+
"model.layers.28.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 493 |
+
"model.layers.28.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 494 |
+
"model.layers.28.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 495 |
+
"model.layers.28.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 496 |
+
"model.layers.28.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 497 |
+
"model.layers.28.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 498 |
+
"model.layers.28.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 499 |
+
"model.layers.28.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 500 |
+
"model.layers.28.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 501 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 502 |
+
"model.layers.28.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 503 |
+
"model.layers.28.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 504 |
+
"model.layers.28.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 505 |
+
"model.layers.28.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 506 |
+
"model.layers.28.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 507 |
+
"model.layers.28.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 508 |
+
"model.layers.28.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 509 |
+
"model.layers.28.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 510 |
+
"model.layers.28.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 511 |
+
"model.layers.28.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 512 |
+
"model.layers.28.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 513 |
+
"model.layers.28.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 514 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 515 |
+
"model.layers.29.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 516 |
+
"model.layers.29.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 517 |
+
"model.layers.29.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 518 |
+
"model.layers.29.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 519 |
+
"model.layers.29.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 520 |
+
"model.layers.29.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 521 |
+
"model.layers.29.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 522 |
+
"model.layers.29.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 523 |
+
"model.layers.29.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 524 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 525 |
+
"model.layers.29.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 526 |
+
"model.layers.29.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 527 |
+
"model.layers.29.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 528 |
+
"model.layers.29.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 529 |
+
"model.layers.29.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 530 |
+
"model.layers.29.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 531 |
+
"model.layers.29.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 532 |
+
"model.layers.29.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 533 |
+
"model.layers.29.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 534 |
+
"model.layers.29.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 535 |
+
"model.layers.29.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 536 |
+
"model.layers.29.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 537 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 538 |
+
"model.layers.3.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 539 |
+
"model.layers.3.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 540 |
+
"model.layers.3.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 541 |
+
"model.layers.3.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 542 |
+
"model.layers.3.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 543 |
+
"model.layers.3.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 544 |
+
"model.layers.3.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 545 |
+
"model.layers.3.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 546 |
+
"model.layers.3.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 547 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 548 |
+
"model.layers.3.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 549 |
+
"model.layers.3.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 550 |
+
"model.layers.3.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 551 |
+
"model.layers.3.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 552 |
+
"model.layers.3.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 553 |
+
"model.layers.3.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 554 |
+
"model.layers.3.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 555 |
+
"model.layers.3.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 556 |
+
"model.layers.3.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 557 |
+
"model.layers.3.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 558 |
+
"model.layers.3.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 559 |
+
"model.layers.3.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 560 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 561 |
+
"model.layers.30.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 562 |
+
"model.layers.30.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 563 |
+
"model.layers.30.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 564 |
+
"model.layers.30.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 565 |
+
"model.layers.30.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 566 |
+
"model.layers.30.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 567 |
+
"model.layers.30.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 568 |
+
"model.layers.30.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 569 |
+
"model.layers.30.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 570 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 571 |
+
"model.layers.30.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 572 |
+
"model.layers.30.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 573 |
+
"model.layers.30.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 574 |
+
"model.layers.30.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 575 |
+
"model.layers.30.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 576 |
+
"model.layers.30.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 577 |
+
"model.layers.30.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 578 |
+
"model.layers.30.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 579 |
+
"model.layers.30.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 580 |
+
"model.layers.30.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 581 |
+
"model.layers.30.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 582 |
+
"model.layers.30.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 583 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 584 |
+
"model.layers.31.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 585 |
+
"model.layers.31.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 586 |
+
"model.layers.31.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 587 |
+
"model.layers.31.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 588 |
+
"model.layers.31.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 589 |
+
"model.layers.31.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 590 |
+
"model.layers.31.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 591 |
+
"model.layers.31.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 592 |
+
"model.layers.31.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 593 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 594 |
+
"model.layers.31.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 595 |
+
"model.layers.31.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 596 |
+
"model.layers.31.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 597 |
+
"model.layers.31.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 598 |
+
"model.layers.31.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 599 |
+
"model.layers.31.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 600 |
+
"model.layers.31.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 601 |
+
"model.layers.31.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 602 |
+
"model.layers.31.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 603 |
+
"model.layers.31.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 604 |
+
"model.layers.31.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 605 |
+
"model.layers.31.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 606 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 607 |
+
"model.layers.32.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 608 |
+
"model.layers.32.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 609 |
+
"model.layers.32.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 610 |
+
"model.layers.32.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 611 |
+
"model.layers.32.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 612 |
+
"model.layers.32.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 613 |
+
"model.layers.32.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 614 |
+
"model.layers.32.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 615 |
+
"model.layers.32.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 616 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 617 |
+
"model.layers.32.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 618 |
+
"model.layers.32.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 619 |
+
"model.layers.32.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 620 |
+
"model.layers.32.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 621 |
+
"model.layers.32.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 622 |
+
"model.layers.32.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 623 |
+
"model.layers.32.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 624 |
+
"model.layers.32.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 625 |
+
"model.layers.32.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 626 |
+
"model.layers.32.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 627 |
+
"model.layers.32.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 628 |
+
"model.layers.32.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 629 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 630 |
+
"model.layers.33.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 631 |
+
"model.layers.33.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 632 |
+
"model.layers.33.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 633 |
+
"model.layers.33.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 634 |
+
"model.layers.33.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 635 |
+
"model.layers.33.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 636 |
+
"model.layers.33.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 637 |
+
"model.layers.33.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 638 |
+
"model.layers.33.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 639 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 640 |
+
"model.layers.33.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 641 |
+
"model.layers.33.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 642 |
+
"model.layers.33.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 643 |
+
"model.layers.33.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 644 |
+
"model.layers.33.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 645 |
+
"model.layers.33.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 646 |
+
"model.layers.33.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 647 |
+
"model.layers.33.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 648 |
+
"model.layers.33.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 649 |
+
"model.layers.33.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 650 |
+
"model.layers.33.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 651 |
+
"model.layers.33.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 652 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 653 |
+
"model.layers.34.mlp.down_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 654 |
+
"model.layers.34.mlp.down_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 655 |
+
"model.layers.34.mlp.down_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 656 |
+
"model.layers.34.mlp.gate_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 657 |
+
"model.layers.34.mlp.gate_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 658 |
+
"model.layers.34.mlp.gate_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 659 |
+
"model.layers.34.mlp.up_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 660 |
+
"model.layers.34.mlp.up_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 661 |
+
"model.layers.34.mlp.up_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 662 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
| 663 |
+
"model.layers.34.self_attn.k_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 664 |
+
"model.layers.34.self_attn.k_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 665 |
+
"model.layers.34.self_attn.k_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 666 |
+
"model.layers.34.self_attn.o_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 667 |
+
"model.layers.34.self_attn.o_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 668 |
+
"model.layers.34.self_attn.o_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 669 |
+
"model.layers.34.self_attn.q_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 670 |
+
"model.layers.34.self_attn.q_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 671 |
+
"model.layers.34.self_attn.q_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 672 |
+
"model.layers.34.self_attn.v_proj.qweight": "pytorch_model-00002-of-00004.bin",
|
| 673 |
+
"model.layers.34.self_attn.v_proj.qzeros": "pytorch_model-00002-of-00004.bin",
|
| 674 |
+
"model.layers.34.self_attn.v_proj.scales": "pytorch_model-00002-of-00004.bin",
|
| 675 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 676 |
+
"model.layers.35.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 677 |
+
"model.layers.35.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 678 |
+
"model.layers.35.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 679 |
+
"model.layers.35.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 680 |
+
"model.layers.35.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 681 |
+
"model.layers.35.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 682 |
+
"model.layers.35.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 683 |
+
"model.layers.35.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 684 |
+
"model.layers.35.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 685 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 686 |
+
"model.layers.35.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 687 |
+
"model.layers.35.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 688 |
+
"model.layers.35.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 689 |
+
"model.layers.35.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 690 |
+
"model.layers.35.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 691 |
+
"model.layers.35.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 692 |
+
"model.layers.35.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 693 |
+
"model.layers.35.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 694 |
+
"model.layers.35.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 695 |
+
"model.layers.35.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 696 |
+
"model.layers.35.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 697 |
+
"model.layers.35.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 698 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 699 |
+
"model.layers.36.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 700 |
+
"model.layers.36.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 701 |
+
"model.layers.36.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 702 |
+
"model.layers.36.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 703 |
+
"model.layers.36.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 704 |
+
"model.layers.36.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 705 |
+
"model.layers.36.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 706 |
+
"model.layers.36.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 707 |
+
"model.layers.36.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 708 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 709 |
+
"model.layers.36.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 710 |
+
"model.layers.36.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 711 |
+
"model.layers.36.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 712 |
+
"model.layers.36.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 713 |
+
"model.layers.36.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 714 |
+
"model.layers.36.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 715 |
+
"model.layers.36.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 716 |
+
"model.layers.36.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 717 |
+
"model.layers.36.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 718 |
+
"model.layers.36.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 719 |
+
"model.layers.36.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 720 |
+
"model.layers.36.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 721 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 722 |
+
"model.layers.37.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 723 |
+
"model.layers.37.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 724 |
+
"model.layers.37.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 725 |
+
"model.layers.37.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 726 |
+
"model.layers.37.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 727 |
+
"model.layers.37.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 728 |
+
"model.layers.37.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 729 |
+
"model.layers.37.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 730 |
+
"model.layers.37.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 731 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 732 |
+
"model.layers.37.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 733 |
+
"model.layers.37.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 734 |
+
"model.layers.37.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 735 |
+
"model.layers.37.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 736 |
+
"model.layers.37.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 737 |
+
"model.layers.37.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 738 |
+
"model.layers.37.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 739 |
+
"model.layers.37.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 740 |
+
"model.layers.37.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 741 |
+
"model.layers.37.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 742 |
+
"model.layers.37.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 743 |
+
"model.layers.37.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 744 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 745 |
+
"model.layers.38.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 746 |
+
"model.layers.38.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 747 |
+
"model.layers.38.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 748 |
+
"model.layers.38.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 749 |
+
"model.layers.38.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 750 |
+
"model.layers.38.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 751 |
+
"model.layers.38.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 752 |
+
"model.layers.38.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 753 |
+
"model.layers.38.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 754 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 755 |
+
"model.layers.38.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 756 |
+
"model.layers.38.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 757 |
+
"model.layers.38.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 758 |
+
"model.layers.38.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 759 |
+
"model.layers.38.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 760 |
+
"model.layers.38.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 761 |
+
"model.layers.38.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 762 |
+
"model.layers.38.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 763 |
+
"model.layers.38.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 764 |
+
"model.layers.38.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 765 |
+
"model.layers.38.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 766 |
+
"model.layers.38.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 767 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 768 |
+
"model.layers.39.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 769 |
+
"model.layers.39.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 770 |
+
"model.layers.39.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 771 |
+
"model.layers.39.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 772 |
+
"model.layers.39.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 773 |
+
"model.layers.39.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 774 |
+
"model.layers.39.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 775 |
+
"model.layers.39.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 776 |
+
"model.layers.39.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 777 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 778 |
+
"model.layers.39.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 779 |
+
"model.layers.39.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 780 |
+
"model.layers.39.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 781 |
+
"model.layers.39.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 782 |
+
"model.layers.39.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 783 |
+
"model.layers.39.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 784 |
+
"model.layers.39.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 785 |
+
"model.layers.39.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 786 |
+
"model.layers.39.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 787 |
+
"model.layers.39.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 788 |
+
"model.layers.39.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 789 |
+
"model.layers.39.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 790 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 791 |
+
"model.layers.4.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 792 |
+
"model.layers.4.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 793 |
+
"model.layers.4.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 794 |
+
"model.layers.4.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 795 |
+
"model.layers.4.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 796 |
+
"model.layers.4.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 797 |
+
"model.layers.4.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 798 |
+
"model.layers.4.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 799 |
+
"model.layers.4.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 800 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 801 |
+
"model.layers.4.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 802 |
+
"model.layers.4.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 803 |
+
"model.layers.4.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 804 |
+
"model.layers.4.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 805 |
+
"model.layers.4.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 806 |
+
"model.layers.4.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 807 |
+
"model.layers.4.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 808 |
+
"model.layers.4.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 809 |
+
"model.layers.4.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 810 |
+
"model.layers.4.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 811 |
+
"model.layers.4.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 812 |
+
"model.layers.4.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 813 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 814 |
+
"model.layers.40.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 815 |
+
"model.layers.40.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 816 |
+
"model.layers.40.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 817 |
+
"model.layers.40.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 818 |
+
"model.layers.40.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 819 |
+
"model.layers.40.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 820 |
+
"model.layers.40.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 821 |
+
"model.layers.40.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 822 |
+
"model.layers.40.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 823 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 824 |
+
"model.layers.40.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 825 |
+
"model.layers.40.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 826 |
+
"model.layers.40.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 827 |
+
"model.layers.40.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 828 |
+
"model.layers.40.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 829 |
+
"model.layers.40.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 830 |
+
"model.layers.40.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 831 |
+
"model.layers.40.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 832 |
+
"model.layers.40.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 833 |
+
"model.layers.40.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 834 |
+
"model.layers.40.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 835 |
+
"model.layers.40.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 836 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 837 |
+
"model.layers.41.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 838 |
+
"model.layers.41.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 839 |
+
"model.layers.41.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 840 |
+
"model.layers.41.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 841 |
+
"model.layers.41.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 842 |
+
"model.layers.41.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 843 |
+
"model.layers.41.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 844 |
+
"model.layers.41.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 845 |
+
"model.layers.41.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 846 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 847 |
+
"model.layers.41.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 848 |
+
"model.layers.41.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 849 |
+
"model.layers.41.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 850 |
+
"model.layers.41.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 851 |
+
"model.layers.41.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 852 |
+
"model.layers.41.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 853 |
+
"model.layers.41.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 854 |
+
"model.layers.41.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 855 |
+
"model.layers.41.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 856 |
+
"model.layers.41.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 857 |
+
"model.layers.41.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 858 |
+
"model.layers.41.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 859 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 860 |
+
"model.layers.42.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 861 |
+
"model.layers.42.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 862 |
+
"model.layers.42.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 863 |
+
"model.layers.42.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 864 |
+
"model.layers.42.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 865 |
+
"model.layers.42.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 866 |
+
"model.layers.42.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 867 |
+
"model.layers.42.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 868 |
+
"model.layers.42.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 869 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 870 |
+
"model.layers.42.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 871 |
+
"model.layers.42.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 872 |
+
"model.layers.42.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 873 |
+
"model.layers.42.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 874 |
+
"model.layers.42.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 875 |
+
"model.layers.42.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 876 |
+
"model.layers.42.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 877 |
+
"model.layers.42.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 878 |
+
"model.layers.42.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 879 |
+
"model.layers.42.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 880 |
+
"model.layers.42.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 881 |
+
"model.layers.42.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 882 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 883 |
+
"model.layers.43.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 884 |
+
"model.layers.43.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 885 |
+
"model.layers.43.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 886 |
+
"model.layers.43.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 887 |
+
"model.layers.43.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 888 |
+
"model.layers.43.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 889 |
+
"model.layers.43.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 890 |
+
"model.layers.43.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 891 |
+
"model.layers.43.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 892 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 893 |
+
"model.layers.43.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 894 |
+
"model.layers.43.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 895 |
+
"model.layers.43.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 896 |
+
"model.layers.43.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 897 |
+
"model.layers.43.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 898 |
+
"model.layers.43.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 899 |
+
"model.layers.43.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 900 |
+
"model.layers.43.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 901 |
+
"model.layers.43.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 902 |
+
"model.layers.43.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 903 |
+
"model.layers.43.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 904 |
+
"model.layers.43.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 905 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 906 |
+
"model.layers.44.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 907 |
+
"model.layers.44.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 908 |
+
"model.layers.44.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 909 |
+
"model.layers.44.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 910 |
+
"model.layers.44.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 911 |
+
"model.layers.44.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 912 |
+
"model.layers.44.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 913 |
+
"model.layers.44.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 914 |
+
"model.layers.44.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 915 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 916 |
+
"model.layers.44.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 917 |
+
"model.layers.44.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 918 |
+
"model.layers.44.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 919 |
+
"model.layers.44.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 920 |
+
"model.layers.44.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 921 |
+
"model.layers.44.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 922 |
+
"model.layers.44.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 923 |
+
"model.layers.44.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 924 |
+
"model.layers.44.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 925 |
+
"model.layers.44.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 926 |
+
"model.layers.44.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 927 |
+
"model.layers.44.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 928 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 929 |
+
"model.layers.45.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 930 |
+
"model.layers.45.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 931 |
+
"model.layers.45.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 932 |
+
"model.layers.45.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 933 |
+
"model.layers.45.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 934 |
+
"model.layers.45.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 935 |
+
"model.layers.45.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 936 |
+
"model.layers.45.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 937 |
+
"model.layers.45.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 938 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 939 |
+
"model.layers.45.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 940 |
+
"model.layers.45.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 941 |
+
"model.layers.45.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 942 |
+
"model.layers.45.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 943 |
+
"model.layers.45.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 944 |
+
"model.layers.45.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 945 |
+
"model.layers.45.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 946 |
+
"model.layers.45.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 947 |
+
"model.layers.45.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 948 |
+
"model.layers.45.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 949 |
+
"model.layers.45.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 950 |
+
"model.layers.45.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 951 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 952 |
+
"model.layers.46.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 953 |
+
"model.layers.46.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 954 |
+
"model.layers.46.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 955 |
+
"model.layers.46.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 956 |
+
"model.layers.46.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 957 |
+
"model.layers.46.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 958 |
+
"model.layers.46.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 959 |
+
"model.layers.46.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 960 |
+
"model.layers.46.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 961 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 962 |
+
"model.layers.46.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 963 |
+
"model.layers.46.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 964 |
+
"model.layers.46.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 965 |
+
"model.layers.46.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 966 |
+
"model.layers.46.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 967 |
+
"model.layers.46.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 968 |
+
"model.layers.46.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 969 |
+
"model.layers.46.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 970 |
+
"model.layers.46.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 971 |
+
"model.layers.46.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 972 |
+
"model.layers.46.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 973 |
+
"model.layers.46.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 974 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 975 |
+
"model.layers.47.mlp.down_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 976 |
+
"model.layers.47.mlp.down_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 977 |
+
"model.layers.47.mlp.down_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 978 |
+
"model.layers.47.mlp.gate_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 979 |
+
"model.layers.47.mlp.gate_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 980 |
+
"model.layers.47.mlp.gate_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 981 |
+
"model.layers.47.mlp.up_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 982 |
+
"model.layers.47.mlp.up_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 983 |
+
"model.layers.47.mlp.up_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 984 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
| 985 |
+
"model.layers.47.self_attn.k_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 986 |
+
"model.layers.47.self_attn.k_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 987 |
+
"model.layers.47.self_attn.k_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 988 |
+
"model.layers.47.self_attn.o_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 989 |
+
"model.layers.47.self_attn.o_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 990 |
+
"model.layers.47.self_attn.o_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 991 |
+
"model.layers.47.self_attn.q_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 992 |
+
"model.layers.47.self_attn.q_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 993 |
+
"model.layers.47.self_attn.q_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 994 |
+
"model.layers.47.self_attn.v_proj.qweight": "pytorch_model-00003-of-00004.bin",
|
| 995 |
+
"model.layers.47.self_attn.v_proj.qzeros": "pytorch_model-00003-of-00004.bin",
|
| 996 |
+
"model.layers.47.self_attn.v_proj.scales": "pytorch_model-00003-of-00004.bin",
|
| 997 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 998 |
+
"model.layers.5.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 999 |
+
"model.layers.5.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1000 |
+
"model.layers.5.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1001 |
+
"model.layers.5.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1002 |
+
"model.layers.5.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1003 |
+
"model.layers.5.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1004 |
+
"model.layers.5.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1005 |
+
"model.layers.5.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1006 |
+
"model.layers.5.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1007 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1008 |
+
"model.layers.5.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1009 |
+
"model.layers.5.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1010 |
+
"model.layers.5.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1011 |
+
"model.layers.5.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1012 |
+
"model.layers.5.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1013 |
+
"model.layers.5.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1014 |
+
"model.layers.5.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1015 |
+
"model.layers.5.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1016 |
+
"model.layers.5.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1017 |
+
"model.layers.5.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1018 |
+
"model.layers.5.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1019 |
+
"model.layers.5.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1020 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1021 |
+
"model.layers.6.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1022 |
+
"model.layers.6.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1023 |
+
"model.layers.6.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1024 |
+
"model.layers.6.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1025 |
+
"model.layers.6.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1026 |
+
"model.layers.6.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1027 |
+
"model.layers.6.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1028 |
+
"model.layers.6.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1029 |
+
"model.layers.6.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1030 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1031 |
+
"model.layers.6.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1032 |
+
"model.layers.6.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1033 |
+
"model.layers.6.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1034 |
+
"model.layers.6.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1035 |
+
"model.layers.6.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1036 |
+
"model.layers.6.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1037 |
+
"model.layers.6.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1038 |
+
"model.layers.6.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1039 |
+
"model.layers.6.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1040 |
+
"model.layers.6.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1041 |
+
"model.layers.6.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1042 |
+
"model.layers.6.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1043 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1044 |
+
"model.layers.7.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1045 |
+
"model.layers.7.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1046 |
+
"model.layers.7.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1047 |
+
"model.layers.7.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1048 |
+
"model.layers.7.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1049 |
+
"model.layers.7.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1050 |
+
"model.layers.7.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1051 |
+
"model.layers.7.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1052 |
+
"model.layers.7.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1053 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1054 |
+
"model.layers.7.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1055 |
+
"model.layers.7.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1056 |
+
"model.layers.7.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1057 |
+
"model.layers.7.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1058 |
+
"model.layers.7.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1059 |
+
"model.layers.7.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1060 |
+
"model.layers.7.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1061 |
+
"model.layers.7.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1062 |
+
"model.layers.7.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1063 |
+
"model.layers.7.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1064 |
+
"model.layers.7.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1065 |
+
"model.layers.7.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1066 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1067 |
+
"model.layers.8.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1068 |
+
"model.layers.8.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1069 |
+
"model.layers.8.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1070 |
+
"model.layers.8.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1071 |
+
"model.layers.8.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1072 |
+
"model.layers.8.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1073 |
+
"model.layers.8.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1074 |
+
"model.layers.8.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1075 |
+
"model.layers.8.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1076 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1077 |
+
"model.layers.8.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1078 |
+
"model.layers.8.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1079 |
+
"model.layers.8.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1080 |
+
"model.layers.8.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1081 |
+
"model.layers.8.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1082 |
+
"model.layers.8.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1083 |
+
"model.layers.8.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1084 |
+
"model.layers.8.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1085 |
+
"model.layers.8.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1086 |
+
"model.layers.8.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1087 |
+
"model.layers.8.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1088 |
+
"model.layers.8.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1089 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1090 |
+
"model.layers.9.mlp.down_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1091 |
+
"model.layers.9.mlp.down_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1092 |
+
"model.layers.9.mlp.down_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1093 |
+
"model.layers.9.mlp.gate_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1094 |
+
"model.layers.9.mlp.gate_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1095 |
+
"model.layers.9.mlp.gate_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1096 |
+
"model.layers.9.mlp.up_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1097 |
+
"model.layers.9.mlp.up_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1098 |
+
"model.layers.9.mlp.up_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1099 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
| 1100 |
+
"model.layers.9.self_attn.k_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1101 |
+
"model.layers.9.self_attn.k_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1102 |
+
"model.layers.9.self_attn.k_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1103 |
+
"model.layers.9.self_attn.o_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1104 |
+
"model.layers.9.self_attn.o_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1105 |
+
"model.layers.9.self_attn.o_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1106 |
+
"model.layers.9.self_attn.q_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1107 |
+
"model.layers.9.self_attn.q_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1108 |
+
"model.layers.9.self_attn.q_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1109 |
+
"model.layers.9.self_attn.v_proj.qweight": "pytorch_model-00001-of-00004.bin",
|
| 1110 |
+
"model.layers.9.self_attn.v_proj.qzeros": "pytorch_model-00001-of-00004.bin",
|
| 1111 |
+
"model.layers.9.self_attn.v_proj.scales": "pytorch_model-00001-of-00004.bin",
|
| 1112 |
+
"model.norm.weight": "pytorch_model-00003-of-00004.bin"
|
| 1113 |
+
}
|
| 1114 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|action_start|>",
|
| 6 |
+
"<|action_end|>",
|
| 7 |
+
"<|interpreter|>",
|
| 8 |
+
"<|plugin|>",
|
| 9 |
+
"<restate>",
|
| 10 |
+
"</restate>",
|
| 11 |
+
"<planning>",
|
| 12 |
+
"</planning>",
|
| 13 |
+
"<recollect>",
|
| 14 |
+
"</recollect>",
|
| 15 |
+
"<execution>",
|
| 16 |
+
"</execution>",
|
| 17 |
+
"<review>",
|
| 18 |
+
"</review>",
|
| 19 |
+
"<summarize>",
|
| 20 |
+
"</summarize>",
|
| 21 |
+
"<retry>",
|
| 22 |
+
"</retry>",
|
| 23 |
+
"<conclude>",
|
| 24 |
+
"</conclude>"
|
| 25 |
+
],
|
| 26 |
+
"bos_token": {
|
| 27 |
+
"content": "<s>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"eos_token": {
|
| 34 |
+
"content": "</s>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
},
|
| 40 |
+
"pad_token": {
|
| 41 |
+
"content": "</s>",
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"normalized": false,
|
| 44 |
+
"rstrip": false,
|
| 45 |
+
"single_word": false
|
| 46 |
+
},
|
| 47 |
+
"unk_token": {
|
| 48 |
+
"content": "<unk>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": false,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
}
|
| 54 |
+
}
|
tokenization_internlm3.py
ADDED
|
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
from shutil import copyfile
|
| 3 |
+
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
|
| 4 |
+
|
| 5 |
+
import sentencepiece as spm
|
| 6 |
+
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
|
| 7 |
+
from transformers.utils import logging
|
| 8 |
+
|
| 9 |
+
if TYPE_CHECKING:
|
| 10 |
+
from transformers.tokenization_utils_base import TextInput
|
| 11 |
+
|
| 12 |
+
logger = logging.get_logger(__name__)
|
| 13 |
+
|
| 14 |
+
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
|
| 15 |
+
|
| 16 |
+
SPIECE_UNDERLINE = "▁"
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
class InternLM3Tokenizer(PreTrainedTokenizer):
|
| 20 |
+
"""
|
| 21 |
+
Construct a InternLM3 tokenizer. Based on byte-level Byte-Pair-Encoding. The default padding token is unset as there is
|
| 22 |
+
no padding token in the original model.
|
| 23 |
+
|
| 24 |
+
Args:
|
| 25 |
+
vocab_file (`str`):
|
| 26 |
+
Path to the vocabulary file.
|
| 27 |
+
unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<unk>"`):
|
| 28 |
+
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
|
| 29 |
+
token instead.
|
| 30 |
+
bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<s>"`):
|
| 31 |
+
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
|
| 32 |
+
eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"</s>"`):
|
| 33 |
+
The end of sequence token.
|
| 34 |
+
pad_token (`str` or `tokenizers.AddedToken`, *optional*):
|
| 35 |
+
A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by
|
| 36 |
+
attention mechanisms or loss computation.
|
| 37 |
+
sp_model_kwargs (`Dict[str, Any]`, `Optional`, *optional*):
|
| 38 |
+
Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
|
| 39 |
+
SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
|
| 40 |
+
to set:
|
| 41 |
+
|
| 42 |
+
- `enable_sampling`: Enable subword regularization.
|
| 43 |
+
- `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
|
| 44 |
+
|
| 45 |
+
- `nbest_size = {0,1}`: No sampling is performed.
|
| 46 |
+
- `nbest_size > 1`: samples from the nbest_size results.
|
| 47 |
+
- `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
|
| 48 |
+
using forward-filtering-and-backward-sampling algorithm.
|
| 49 |
+
|
| 50 |
+
- `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
|
| 51 |
+
BPE-dropout.
|
| 52 |
+
|
| 53 |
+
add_bos_token (`bool`, *optional*, defaults to `True`):
|
| 54 |
+
Whether or not to add an `bos_token` at the start of sequences.
|
| 55 |
+
add_eos_token (`bool`, *optional*, defaults to `False`):
|
| 56 |
+
Whether or not to add an `eos_token` at the end of sequences.
|
| 57 |
+
clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
|
| 58 |
+
Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
|
| 59 |
+
extra spaces.
|
| 60 |
+
use_default_system_prompt (`bool`, *optional*, defaults to `False`):
|
| 61 |
+
Whether or not the default system prompt for InternLM3 should be used.
|
| 62 |
+
spaces_between_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 63 |
+
Whether or not to add spaces between special tokens.
|
| 64 |
+
spaces_for_interleaved_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 65 |
+
Whether or not to add spaces between special tokens that are interleaved with normal tokens.
|
| 66 |
+
add_prefix_space (`bool`, *optional*, defaults to `True`):
|
| 67 |
+
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
|
| 68 |
+
other word. Again, this should be set with `from_slow=True` to make sure it's taken into account.
|
| 69 |
+
"""
|
| 70 |
+
|
| 71 |
+
vocab_files_names = VOCAB_FILES_NAMES
|
| 72 |
+
model_input_names = ["input_ids", "attention_mask"]
|
| 73 |
+
|
| 74 |
+
def __init__(
|
| 75 |
+
self,
|
| 76 |
+
vocab_file,
|
| 77 |
+
unk_token="<unk>",
|
| 78 |
+
bos_token="<s>",
|
| 79 |
+
eos_token="</s>",
|
| 80 |
+
pad_token=None,
|
| 81 |
+
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
| 82 |
+
add_bos_token=True,
|
| 83 |
+
add_eos_token=False,
|
| 84 |
+
clean_up_tokenization_spaces=False,
|
| 85 |
+
use_default_system_prompt=False,
|
| 86 |
+
spaces_between_special_tokens=False,
|
| 87 |
+
spaces_for_interleaved_special_tokens=False,
|
| 88 |
+
add_prefix_space=True,
|
| 89 |
+
**kwargs,
|
| 90 |
+
):
|
| 91 |
+
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
| 92 |
+
bos_token = AddedToken(bos_token, normalized=False, special=True) if isinstance(bos_token, str) else bos_token
|
| 93 |
+
eos_token = AddedToken(eos_token, normalized=False, special=True) if isinstance(eos_token, str) else eos_token
|
| 94 |
+
unk_token = AddedToken(unk_token, normalized=False, special=True) if isinstance(unk_token, str) else unk_token
|
| 95 |
+
pad_token = AddedToken(pad_token, normalized=False, special=True) if isinstance(pad_token, str) else pad_token
|
| 96 |
+
|
| 97 |
+
self.vocab_file = vocab_file
|
| 98 |
+
self.add_bos_token = add_bos_token
|
| 99 |
+
self.add_eos_token = add_eos_token
|
| 100 |
+
self.use_default_system_prompt = use_default_system_prompt
|
| 101 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 102 |
+
self.sp_model.Load(vocab_file)
|
| 103 |
+
self.add_prefix_space = add_prefix_space
|
| 104 |
+
self.spaces_for_interleaved_special_tokens = spaces_for_interleaved_special_tokens
|
| 105 |
+
|
| 106 |
+
vocab_size = self.sp_model.get_piece_size()
|
| 107 |
+
self.decoder = {i: self.sp_model.id_to_piece(i) for i in range(vocab_size)}
|
| 108 |
+
|
| 109 |
+
super().__init__(
|
| 110 |
+
bos_token=bos_token,
|
| 111 |
+
eos_token=eos_token,
|
| 112 |
+
unk_token=unk_token,
|
| 113 |
+
pad_token=pad_token,
|
| 114 |
+
add_bos_token=add_bos_token,
|
| 115 |
+
add_eos_token=add_eos_token,
|
| 116 |
+
sp_model_kwargs=sp_model_kwargs,
|
| 117 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
| 118 |
+
use_default_system_prompt=use_default_system_prompt,
|
| 119 |
+
spaces_between_special_tokens=spaces_between_special_tokens,
|
| 120 |
+
add_prefix_space=add_prefix_space,
|
| 121 |
+
**kwargs,
|
| 122 |
+
)
|
| 123 |
+
|
| 124 |
+
def __getstate__(self):
|
| 125 |
+
state = self.__dict__.copy()
|
| 126 |
+
state["sp_model"] = None
|
| 127 |
+
state["sp_model_proto"] = self.sp_model.serialized_model_proto()
|
| 128 |
+
return state
|
| 129 |
+
|
| 130 |
+
def __setstate__(self, d):
|
| 131 |
+
self.__dict__.update(d)
|
| 132 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 133 |
+
self.sp_model.LoadFromSerializedProto(self.sp_model_proto)
|
| 134 |
+
|
| 135 |
+
@property
|
| 136 |
+
def vocab_size(self):
|
| 137 |
+
"""Returns vocab size"""
|
| 138 |
+
return self.sp_model.get_piece_size()
|
| 139 |
+
|
| 140 |
+
def get_vocab(self):
|
| 141 |
+
"""Returns vocab as a dict"""
|
| 142 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
| 143 |
+
vocab.update(self.added_tokens_encoder)
|
| 144 |
+
return vocab
|
| 145 |
+
|
| 146 |
+
def tokenize(self, text: "TextInput", **kwargs) -> List[str]:
|
| 147 |
+
"""
|
| 148 |
+
Args:
|
| 149 |
+
text: TextInput
|
| 150 |
+
Simply calls PreTrainedTokenizer's method
|
| 151 |
+
"""
|
| 152 |
+
return super().tokenize(text, **kwargs)
|
| 153 |
+
|
| 154 |
+
def _tokenize(self, text, **kwargs):
|
| 155 |
+
"""
|
| 156 |
+
Args:
|
| 157 |
+
text: TextInput
|
| 158 |
+
Returns a tokenized string. The Gemma tokenizer never adds a prefix space.
|
| 159 |
+
"""
|
| 160 |
+
return self.sp_model.encode(text, out_type=str)
|
| 161 |
+
|
| 162 |
+
def _convert_token_to_id(self, token):
|
| 163 |
+
"""Converts a token (str) in an id using the vocab."""
|
| 164 |
+
return self.sp_model.piece_to_id(token)
|
| 165 |
+
|
| 166 |
+
def _convert_id_to_token(self, index):
|
| 167 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
| 168 |
+
return self.decoder.get(index, "")
|
| 169 |
+
|
| 170 |
+
def convert_tokens_to_string(self, tokens):
|
| 171 |
+
"""Converts a sequence of tokens (string) in a single string."""
|
| 172 |
+
# since we manually add the prefix space, we have to remove it when decoding
|
| 173 |
+
if tokens[0].startswith(SPIECE_UNDERLINE) and self.add_prefix_space:
|
| 174 |
+
tokens[0] = tokens[0][1:]
|
| 175 |
+
|
| 176 |
+
current_sub_tokens = []
|
| 177 |
+
out_string = ""
|
| 178 |
+
prev_is_special = False
|
| 179 |
+
for i, token in enumerate(tokens):
|
| 180 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
| 181 |
+
if token in self.all_special_tokens:
|
| 182 |
+
if not prev_is_special and i != 0 and self.spaces_for_interleaved_special_tokens:
|
| 183 |
+
out_string += " "
|
| 184 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
| 185 |
+
prev_is_special = True
|
| 186 |
+
current_sub_tokens = []
|
| 187 |
+
else:
|
| 188 |
+
if (
|
| 189 |
+
prev_is_special
|
| 190 |
+
and i == 1
|
| 191 |
+
and self.add_prefix_space
|
| 192 |
+
and not token.startswith(SPIECE_UNDERLINE)
|
| 193 |
+
and self.spaces_for_interleaved_special_tokens
|
| 194 |
+
):
|
| 195 |
+
out_string += " "
|
| 196 |
+
current_sub_tokens.append(token)
|
| 197 |
+
prev_is_special = False
|
| 198 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
| 199 |
+
return out_string
|
| 200 |
+
|
| 201 |
+
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
| 202 |
+
"""
|
| 203 |
+
Save the vocabulary and special tokens file to a directory.
|
| 204 |
+
|
| 205 |
+
Args:
|
| 206 |
+
save_directory (`str`):
|
| 207 |
+
The directory in which to save the vocabulary.
|
| 208 |
+
|
| 209 |
+
Returns:
|
| 210 |
+
`Tuple(str)`: Paths to the files saved.
|
| 211 |
+
"""
|
| 212 |
+
if not os.path.isdir(save_directory):
|
| 213 |
+
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
| 214 |
+
return
|
| 215 |
+
out_vocab_file = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"])
|
| 216 |
+
|
| 217 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
| 218 |
+
copyfile(self.vocab_file, out_vocab_file)
|
| 219 |
+
elif not os.path.isfile(self.vocab_file):
|
| 220 |
+
with open(out_vocab_file, "wb") as fi:
|
| 221 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
| 222 |
+
fi.write(content_spiece_model)
|
| 223 |
+
|
| 224 |
+
return (out_vocab_file,)
|
| 225 |
+
|
| 226 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
| 227 |
+
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
| 228 |
+
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
| 229 |
+
|
| 230 |
+
output = bos_token_id + token_ids_0 + eos_token_id
|
| 231 |
+
|
| 232 |
+
if token_ids_1 is not None:
|
| 233 |
+
output = output + bos_token_id + token_ids_1 + eos_token_id
|
| 234 |
+
|
| 235 |
+
return output
|
| 236 |
+
|
| 237 |
+
def get_special_tokens_mask(
|
| 238 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
| 239 |
+
) -> List[int]:
|
| 240 |
+
"""
|
| 241 |
+
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
| 242 |
+
special tokens using the tokenizer `prepare_for_model` method.
|
| 243 |
+
|
| 244 |
+
Args:
|
| 245 |
+
token_ids_0 (`List[int]`):
|
| 246 |
+
List of IDs.
|
| 247 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 248 |
+
Optional second list of IDs for sequence pairs.
|
| 249 |
+
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 250 |
+
Whether or not the token list is already formatted with special tokens for the model.
|
| 251 |
+
|
| 252 |
+
Returns:
|
| 253 |
+
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
| 254 |
+
"""
|
| 255 |
+
if already_has_special_tokens:
|
| 256 |
+
return super().get_special_tokens_mask(token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True)
|
| 257 |
+
|
| 258 |
+
bos_token_id = [1] if self.add_bos_token else []
|
| 259 |
+
eos_token_id = [1] if self.add_eos_token else []
|
| 260 |
+
|
| 261 |
+
if token_ids_1 is None:
|
| 262 |
+
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
|
| 263 |
+
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + bos_token_id + ([0] * len(token_ids_1)) + eos_token_id
|
| 264 |
+
|
| 265 |
+
def create_token_type_ids_from_sequences(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]:
|
| 266 |
+
"""
|
| 267 |
+
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
|
| 268 |
+
sequence pair mask has the following format:
|
| 269 |
+
|
| 270 |
+
```
|
| 271 |
+
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
|
| 272 |
+
| first sequence | second sequence |
|
| 273 |
+
```
|
| 274 |
+
|
| 275 |
+
if token_ids_1 is None, only returns the first portion of the mask (0s).
|
| 276 |
+
|
| 277 |
+
Args:
|
| 278 |
+
token_ids_0 (`List[int]`):
|
| 279 |
+
List of ids.
|
| 280 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 281 |
+
Optional second list of IDs for sequence pairs.
|
| 282 |
+
|
| 283 |
+
Returns:
|
| 284 |
+
`List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
|
| 285 |
+
"""
|
| 286 |
+
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
|
| 287 |
+
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
|
| 288 |
+
|
| 289 |
+
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
|
| 290 |
+
|
| 291 |
+
if token_ids_1 is not None:
|
| 292 |
+
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
|
| 293 |
+
|
| 294 |
+
return output
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcacff3229854f5103ee7a85473a30ca9a8b3a68f3aae9b7479574b23ac2256b
|
| 3 |
+
size 2475075
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,249 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128111": {
|
| 31 |
+
"content": "<restate>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128112": {
|
| 39 |
+
"content": "</restate>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128113": {
|
| 47 |
+
"content": "<planning>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128114": {
|
| 55 |
+
"content": "</planning>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128115": {
|
| 63 |
+
"content": "<recollect>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128116": {
|
| 71 |
+
"content": "</recollect>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128117": {
|
| 79 |
+
"content": "<execution>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128118": {
|
| 87 |
+
"content": "</execution>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128119": {
|
| 95 |
+
"content": "<review>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"128120": {
|
| 103 |
+
"content": "</review>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"128121": {
|
| 111 |
+
"content": "<summarize>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"128122": {
|
| 119 |
+
"content": "</summarize>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"128123": {
|
| 127 |
+
"content": "<retry>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128124": {
|
| 135 |
+
"content": "</retry>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128125": {
|
| 143 |
+
"content": "<conclude>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128126": {
|
| 151 |
+
"content": "</conclude>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128127": {
|
| 159 |
+
"content": "<|plugin|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128128": {
|
| 167 |
+
"content": "<|interpreter|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128129": {
|
| 175 |
+
"content": "<|action_end|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128130": {
|
| 183 |
+
"content": "<|action_start|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128131": {
|
| 191 |
+
"content": "<|im_end|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128132": {
|
| 199 |
+
"content": "<|im_start|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"additional_special_tokens": [
|
| 208 |
+
"<|im_start|>",
|
| 209 |
+
"<|im_end|>",
|
| 210 |
+
"<|action_start|>",
|
| 211 |
+
"<|action_end|>",
|
| 212 |
+
"<|interpreter|>",
|
| 213 |
+
"<|plugin|>",
|
| 214 |
+
"<restate>",
|
| 215 |
+
"</restate>",
|
| 216 |
+
"<planning>",
|
| 217 |
+
"</planning>",
|
| 218 |
+
"<recollect>",
|
| 219 |
+
"</recollect>",
|
| 220 |
+
"<execution>",
|
| 221 |
+
"</execution>",
|
| 222 |
+
"<review>",
|
| 223 |
+
"</review>",
|
| 224 |
+
"<summarize>",
|
| 225 |
+
"</summarize>",
|
| 226 |
+
"<retry>",
|
| 227 |
+
"</retry>",
|
| 228 |
+
"<conclude>",
|
| 229 |
+
"</conclude>"
|
| 230 |
+
],
|
| 231 |
+
"auto_map": {
|
| 232 |
+
"AutoTokenizer": [
|
| 233 |
+
"tokenization_internlm3.InternLM3Tokenizer",
|
| 234 |
+
null
|
| 235 |
+
]
|
| 236 |
+
},
|
| 237 |
+
"bos_token": "<s>",
|
| 238 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 239 |
+
"clean_up_tokenization_spaces": false,
|
| 240 |
+
"eos_token": "</s>",
|
| 241 |
+
"extra_special_tokens": {},
|
| 242 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 243 |
+
"pad_token": "</s>",
|
| 244 |
+
"sp_model_kwargs": {},
|
| 245 |
+
"spaces_between_special_tokens": false,
|
| 246 |
+
"tokenizer_class": "InternLM3Tokenizer",
|
| 247 |
+
"unk_token": "<unk>",
|
| 248 |
+
"use_default_system_prompt": false
|
| 249 |
+
}
|