Upload MPTForCausalLM

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "mosaicml/mpt-7b",
+  "architectures": [
+    "MPTForCausalLM"
+  ],
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 4096,
+  "emb_pdrop": 0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0,
+    "init_nonlinearity": "relu",
+    "init_std": 0.02,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": true,
+  "logit_scale": null,
+  "max_seq_len": 2048,
+  "model_type": "mpt",
+  "n_heads": 32,
+  "n_layers": 32,
+  "no_bias": true,
+  "norm_type": "low_precision_layernorm",
+  "resid_pdrop": 0,
+  "tokenizer_name": "EleutherAI/gpt-neox-20b",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "verbose": 0,
+  "vocab_size": 50432
+}

configuration_mpt.py

@@ -0,0 +1,118 @@
+"""A HuggingFace-style model configuration."""
+from typing import Dict, Optional, Union
+from transformers import PretrainedConfig
+attn_config_defaults: Dict = {'attn_type': 'multihead_attention', 'attn_pdrop': 0.0, 'attn_impl': 'triton', 'qk_ln': False, 'clip_qkv': None, 'softmax_scale': None, 'prefix_lm': False, 'attn_uses_sequence_id': False, 'alibi': False, 'alibi_bias_max': 8}
+init_config_defaults: Dict = {'name': 'kaiming_normal_', 'fan_mode': 'fan_in', 'init_nonlinearity': 'relu', 'init_div_is_residual': True, 'emb_init_std': None, 'emb_init_uniform_lim': None, 'init_std': None, 'init_gain': 0.0}
+
+class MPTConfig(PretrainedConfig):
+    model_type = 'mpt'
+
+    def __init__(self, d_model: int=2048, n_heads: int=16, n_layers: int=24, expansion_ratio: int=4, max_seq_len: int=2048, vocab_size: int=50368, resid_pdrop: float=0.0, emb_pdrop: float=0.0, learned_pos_emb: bool=True, attn_config: Dict=attn_config_defaults, init_device: str='cpu', logit_scale: Optional[Union[float, str]]=None, no_bias: bool=False, verbose: int=0, embedding_fraction: float=1.0, norm_type: str='low_precision_layernorm', use_cache: bool=False, init_config: Dict=init_config_defaults, **kwargs):
+        """The MPT configuration class.
+
+        Args:
+            d_model (int): The size of the embedding dimension of the model.
+            n_heads (int): The number of attention heads.
+            n_layers (int): The number of layers in the model.
+            expansion_ratio (int): The ratio of the up/down scale in the MLP.
+            max_seq_len (int): The maximum sequence length of the model.
+            vocab_size (int): The size of the vocabulary.
+            resid_pdrop (float): The dropout probability applied to the attention output before combining with residual.
+            emb_pdrop (float): The dropout probability for the embedding layer.
+            learned_pos_emb (bool): Whether to use learned positional embeddings
+            attn_config (Dict):  A dictionary used to configure the model's attention module:
+                attn_type (str): type of attention to use. Options: multihead_attention, multiquery_attention
+                attn_pdrop (float): The dropout probability for the attention layers.
+                attn_impl (str): The attention implementation to use. One of 'torch', 'flash', or 'triton'.
+                qk_ln (bool): Whether to apply layer normalization to the queries and keys in the attention layer.
+                clip_qkv (Optional[float]): If not None, clip the queries, keys, and values in the attention layer to
+                    this value.
+                softmax_scale (Optional[float]): If not None, scale the softmax in the attention layer by this value. If None,
+                    use the default scale of ``1/sqrt(d_keys)``.
+                prefix_lm (Optional[bool]): Whether the model should operate as a Prefix LM. This requires passing an
+                    extra `prefix_mask` argument which indicates which tokens belong to the prefix. Tokens in the prefix
+                    can attend to one another bi-directionally. Tokens outside the prefix use causal attention.
+                attn_uses_sequence_id (Optional[bool]): Whether to restrict attention to tokens that have the same sequence_id.
+                    When the model is in `train` mode, this requires passing an extra `sequence_id` argument which indicates
+                    which sub-sequence each token belongs to.
+                    Defaults to ``False`` meaning any provided `sequence_id` will be ignored.
+                alibi (bool): Whether to use the alibi bias instead of position embeddings.
+                alibi_bias_max (int): The maximum value of the alibi bias.
+            init_device (str): The device to use for parameter initialization.
+            logit_scale (Optional[Union[float, str]]): If not None, scale the logits by this value.
+            no_bias (bool): Whether to use bias in all layers.
+            verbose (int): The verbosity level. 0 is silent.
+            embedding_fraction (float): The fraction to scale the gradients of the embedding layer by.
+            norm_type (str): choose type of norm to use
+            multiquery_attention (bool): Whether to use multiquery attention implementation.
+            use_cache (bool): Whether or not the model should return the last key/values attentions
+            init_config (Dict): A dictionary used to configure the model initialization:
+                init_config.name: The parameter initialization scheme to use. Options: 'default_', 'baseline_',
+                    'kaiming_uniform_', 'kaiming_normal_', 'neox_init_', 'small_init_', 'xavier_uniform_', or
+                    'xavier_normal_'. These mimic the parameter initialization methods in PyTorch.
+                init_div_is_residual (Union[int, float, str, bool]): Value to divide initial weights by if ``module._is_residual`` is True.
+                emb_init_std (Optional[float]): The standard deviation of the normal distribution used to initialize the embedding layer.
+                emb_init_uniform_lim (Optional[Union[Tuple[float, float], float]]): The lower and upper limits of the uniform distribution
+                    used to initialize the embedding layer. Mutually exclusive with ``emb_init_std``.
+                init_std (float): The standard deviation of the normal distribution used to initialize the model,
+                    if using the baseline_ parameter initialization scheme.
+                init_gain (float): The gain to use for parameter initialization with kaiming or xavier initialization schemes.
+                fan_mode (str): The fan mode to use for parameter initialization with kaiming initialization schemes.
+                init_nonlinearity (str): The nonlinearity to use for parameter initialization with kaiming initialization schemes.
+                ---
+                See llmfoundry.models.utils.param_init_fns.py for info on other param init config options
+        """
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.expansion_ratio = expansion_ratio
+        self.max_seq_len = max_seq_len
+        self.vocab_size = vocab_size
+        self.resid_pdrop = resid_pdrop
+        self.emb_pdrop = emb_pdrop
+        self.learned_pos_emb = learned_pos_emb
+        self.attn_config = attn_config
+        self.init_device = init_device
+        self.logit_scale = logit_scale
+        self.no_bias = no_bias
+        self.verbose = verbose
+        self.embedding_fraction = embedding_fraction
+        self.norm_type = norm_type
+        self.use_cache = use_cache
+        self.init_config = init_config
+        if 'name' in kwargs:
+            del kwargs['name']
+        if 'loss_fn' in kwargs:
+            del kwargs['loss_fn']
+        super().__init__(**kwargs)
+        self._validate_config()
+
+    def _set_config_defaults(self, config, config_defaults):
+        for (k, v) in config_defaults.items():
+            if k not in config:
+                config[k] = v
+        return config
+
+    def _validate_config(self):
+        self.attn_config = self._set_config_defaults(self.attn_config, attn_config_defaults)
+        self.init_config = self._set_config_defaults(self.init_config, init_config_defaults)
+        if self.d_model % self.n_heads != 0:
+            raise ValueError('d_model must be divisible by n_heads')
+        if any((prob < 0 or prob > 1 for prob in [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop])):
+            raise ValueError("self.attn_config['attn_pdrop'], resid_pdrop, emb_pdrop are probabilities and must be between 0 and 1")
+        if self.attn_config['attn_impl'] not in ['torch', 'flash', 'triton']:
+            raise ValueError(f"Unknown attn_impl={self.attn_config['attn_impl']}")
+        if self.attn_config['prefix_lm'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('prefix_lm only implemented with torch and triton attention.')
+        if self.attn_config['alibi'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('alibi only implemented with torch and triton attention.')
+        if self.attn_config['attn_uses_sequence_id'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('attn_uses_sequence_id only implemented with torch and triton attention.')
+        if self.embedding_fraction > 1 or self.embedding_fraction <= 0:
+            raise ValueError('model.embedding_fraction must be between 0 (exclusive) and 1 (inclusive)!')
+        if isinstance(self.logit_scale, str) and self.logit_scale != 'inv_sqrt_d_model':
+            raise ValueError(f"self.logit_scale={self.logit_scale!r} is not recognized as an option; use numeric value or 'inv_sqrt_d_model'.")
+        if self.init_config.get('name', None) is None:
+            raise ValueError(f"self.init_config={self.init_config!r} 'name' needs to be set.")
+        if not self.learned_pos_emb and (not self.attn_config['alibi']):
+            raise ValueError(f'Positional information must be provided to the model using either learned_pos_emb or alibi.')

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.28.1",
+  "use_cache": false
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53786eddecce2d9d9a5dd7e531eb23750a45f498e165e37a12c50583d08f216f
+size 9953500837

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78a12c4d4329f061c364b4371e6b469ce5e77fa1d8884329b836680a66b25a2
+size 9932530109

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d25536c68b4678745e8d46aa713d63241ffcdc398fca7e555676517141505f9
+size 6711181899

pytorch_model.bin.index.json

@@ -0,0 +1,201 @@
+{
+  "metadata": {
+    "total_size": 26597146624
+  },
+  "weight_map": {
+    "transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.12.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.12.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.13.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.14.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.15.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.16.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.17.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.18.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.19.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.20.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.20.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.21.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.22.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.23.norm_1.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.23.norm_2.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.24.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.24.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.25.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.26.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.27.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.28.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.29.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.30.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.30.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.norm_1.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.31.norm_2.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.norm_f.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}