MostafaDorrah
commited on
Commit
•
78dc4c9
1
Parent(s):
a9345bd
Upload folder using huggingface_hub
Browse files- README.md +37 -0
- config.json +31 -0
- mergekit_config.yml +18 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +193 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- deepseek-ai/deepseek-coder-6.7b-instruct
|
8 |
+
- ise-uiuc/Magicoder-DS-6.7B
|
9 |
+
---
|
10 |
+
|
11 |
+
# Magicdeep_7b_ultimite_chatbot
|
12 |
+
|
13 |
+
Magicdeep_7b_ultimite_chatbot is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct)
|
15 |
+
* [ise-uiuc/Magicoder-DS-6.7B](https://huggingface.co/ise-uiuc/Magicoder-DS-6.7B)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
models:
|
21 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
22 |
+
# no parameters necessary for base model
|
23 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
24 |
+
parameters:
|
25 |
+
density: 0.5
|
26 |
+
weight: 0.5
|
27 |
+
- model: ise-uiuc/Magicoder-DS-6.7B
|
28 |
+
parameters:
|
29 |
+
density: 0.5
|
30 |
+
weight: 0.3
|
31 |
+
merge_method: ties
|
32 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
33 |
+
parameters:
|
34 |
+
normalize: true
|
35 |
+
dtype: float16
|
36 |
+
|
37 |
+
```
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 32013,
|
9 |
+
"eos_token_id": 32021,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 32,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": {
|
22 |
+
"factor": 4.0,
|
23 |
+
"type": "linear"
|
24 |
+
},
|
25 |
+
"rope_theta": 100000,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float16",
|
28 |
+
"transformers_version": "4.38.1",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32256
|
31 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
4 |
+
# no parameters necessary for base model
|
5 |
+
- model: deepseek-ai/deepseek-coder-6.7b-instruct
|
6 |
+
parameters:
|
7 |
+
density: 0.5
|
8 |
+
weight: 0.5
|
9 |
+
- model: ise-uiuc/Magicoder-DS-6.7B
|
10 |
+
parameters:
|
11 |
+
density: 0.5
|
12 |
+
weight: 0.3
|
13 |
+
merge_method: ties
|
14 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
15 |
+
parameters:
|
16 |
+
normalize: true
|
17 |
+
dtype: float16
|
18 |
+
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db6b0f35e2f179444200b2516fc7521da690e669e08ccf9c47c6a32ab702b49d
|
3 |
+
size 1933644496
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc63af3a92911ed03f2315df40888ef687768965d3043a8ec9b53c2486358c2f
|
3 |
+
size 1927352816
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92588f0581dfbda787111b36352ba9ed15a545c7918ad3fc6c89e02a0c7f5611
|
3 |
+
size 1933661112
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62e2e53b25685c9194fbc0efad7b707572cb8352690ee6af5787f6e17d5cc78b
|
3 |
+
size 1990275944
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c72af34daa40ddfa255453f767b3a033982eb31f5c8b538d6581ba2dd8cb8de9
|
3 |
+
size 1990292544
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9310eef44870b25eb1a006be056014b8a3f6e80e8c5cbfe546e1af89b9a2bcc2
|
3 |
+
size 1990275952
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68d57399920d681f68459e6094b1aff12bcec9593397b993bc692da05dd10b6f
|
3 |
+
size 1715556136
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.embed_tokens.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|EOT|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"32000": {
|
6 |
+
"content": "õ",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": false
|
12 |
+
},
|
13 |
+
"32001": {
|
14 |
+
"content": "÷",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": false
|
20 |
+
},
|
21 |
+
"32002": {
|
22 |
+
"content": "Á",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32003": {
|
30 |
+
"content": "ý",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"32004": {
|
38 |
+
"content": "À",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"32005": {
|
46 |
+
"content": "ÿ",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"32006": {
|
54 |
+
"content": "ø",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"32007": {
|
62 |
+
"content": "ú",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"32008": {
|
70 |
+
"content": "þ",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": true,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"32009": {
|
78 |
+
"content": "ü",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"32010": {
|
86 |
+
"content": "ù",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": true,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"32011": {
|
94 |
+
"content": "ö",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": true,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"32012": {
|
102 |
+
"content": "û",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"32013": {
|
110 |
+
"content": "<|begin▁of▁sentence|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": true,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32014": {
|
118 |
+
"content": "<|end▁of▁sentence|>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": true,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"32015": {
|
126 |
+
"content": "<|fim▁hole|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": true,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"32016": {
|
134 |
+
"content": "<|fim▁begin|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": true,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"32017": {
|
142 |
+
"content": "<|fim▁end|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": true,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"32018": {
|
150 |
+
"content": "<pad>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": true,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"32019": {
|
158 |
+
"content": "<|User|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": true,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"32020": {
|
166 |
+
"content": "<|Assistant|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": true,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"32021": {
|
174 |
+
"content": "<|EOT|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": true,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
183 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
184 |
+
"clean_up_tokenization_spaces": false,
|
185 |
+
"eos_token": "<|EOT|>",
|
186 |
+
"legacy": true,
|
187 |
+
"model_max_length": 16384,
|
188 |
+
"pad_token": "<|end▁of▁sentence|>",
|
189 |
+
"sp_model_kwargs": {},
|
190 |
+
"tokenizer_class": "LlamaTokenizer",
|
191 |
+
"unk_token": null,
|
192 |
+
"use_default_system_prompt": false
|
193 |
+
}
|