reign12 commited on
Commit
b62406c
·
verified ·
1 Parent(s): 8c5a3f2

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "/mnt/step2-alignment-jfs/zane/opensources_model/Qwen2.5-32B",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -11,19 +10,18 @@
11
  "initializer_range": 0.02,
12
  "intermediate_size": 27648,
13
  "max_position_embeddings": 131072,
14
- "max_window_layers": 64,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 40,
17
  "num_hidden_layers": 64,
18
  "num_key_value_heads": 8,
19
  "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
  "rope_theta": 1000000.0,
22
- "sliding_window": null,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.46.1",
26
- "use_cache": false,
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
- }
 
1
  {
 
2
  "architectures": [
3
  "Qwen2ForCausalLM"
4
  ],
 
10
  "initializer_range": 0.02,
11
  "intermediate_size": 27648,
12
  "max_position_embeddings": 131072,
13
+ "max_window_layers": 70,
14
  "model_type": "qwen2",
15
  "num_attention_heads": 40,
16
  "num_hidden_layers": 64,
17
  "num_key_value_heads": 8,
18
  "rms_norm_eps": 1e-05,
 
19
  "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
  "use_sliding_window": false,
26
  "vocab_size": 152064
27
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72752bbdb84b52de8953ecb5bed6be0fb4b972f56431aab85c4319d9846a2beb
3
+ size 12813971088
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8c0c9c632673ed4ce42162be30cb11ee04edd21cfee4225f94837743050de4
3
+ size 13705416016
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b826ad70084614aac514f686575bada6069f610e76af8a914e5b0f99494429f
3
+ size 14219197672
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4d8d033ed89f21f618bf52f507c58330fb91e1ee39615a9a8c05d73835013d
3
+ size 13936082040
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a2cb250c065bc2f86d8530b163b9c782d3a7fef2ec9a4ec1e5756501e34e5a
3
+ size 10853174920
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8506e7111b80c6d8635951a02eab0f4e1a8e4e5772da83846579e97b16f61bf
3
+ size 7031673
tokenizer_config.json CHANGED
@@ -195,7 +195,7 @@
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
- "chat_template": "{{ bos_token }}A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>. {% for message in messages %}{% if message['role'] == 'user' %}User: You must put your answer inside <answer> </answer> tags, i.e., <answer> answer here </answer>. And your final answer will be extracted automatically by the \\boxed{} tag.\nThis is the problem:\n{{ message['content'] }}\n{% elif message['role'] == 'assistant' %}Assistant: <think>{{ message['content'] }}</answer>\n{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant: <think>{% endif %}",
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|endoftext|>",
201
  "errors": "replace",
 
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
+ "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n{%- else %}\n {{- 'A conversation between User and Assistant. The User asks a question, and the Assistant solves it. The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, i.e., <think> reasoning process here </think> <answer> answer here </answer>. ' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") %}\n {{- 'User: ' + message.content + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- 'Assistant: <think>' + message.content + '\\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- 'Assistant: <think>' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|endoftext|>",
201
  "errors": "replace",