Kaballas commited on
Commit
cede32c
1 Parent(s): 9ec91be

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
2
  base_model:
3
- - bunnycore/Qwen2.5-7B-CyberRombos
4
  - jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
5
- - Kaballas/TLetsgo
6
- - C10X/CoT-2.5
7
  - DrNicefellow/Qwen2.5-7B-O1-Journey-1
8
- - djuna/Q2.5-Fuppavy-7B
 
 
 
9
  library_name: transformers
10
  tags:
11
  - mergekit
@@ -19,16 +20,17 @@ This is a merge of pre-trained language models created using [mergekit](https://
19
  ## Merge Details
20
  ### Merge Method
21
 
22
- This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Kaballas/TLetsgo](https://huggingface.co/Kaballas/TLetsgo) as a base.
23
 
24
  ### Models Merged
25
 
26
  The following models were included in the merge:
27
- * [bunnycore/Qwen2.5-7B-CyberRombos](https://huggingface.co/bunnycore/Qwen2.5-7B-CyberRombos)
28
  * [jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7)
29
- * [C10X/CoT-2.5](https://huggingface.co/C10X/CoT-2.5)
30
  * [DrNicefellow/Qwen2.5-7B-O1-Journey-1](https://huggingface.co/DrNicefellow/Qwen2.5-7B-O1-Journey-1)
31
- * [djuna/Q2.5-Fuppavy-7B](https://huggingface.co/djuna/Q2.5-Fuppavy-7B)
 
 
32
 
33
  ### Configuration
34
 
@@ -40,9 +42,10 @@ models:
40
  - model: C10X/CoT-2.5
41
  - model: bunnycore/Qwen2.5-7B-CyberRombos
42
  - model: djuna/Q2.5-Fuppavy-7B
 
43
  - model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
44
 
45
  merge_method: model_stock
46
- base_model: Kaballas/TLetsgo
47
  dtype: bfloat16
48
  ```
 
1
  ---
2
  base_model:
3
+ - djuna/Q2.5-Fuppavy-7B
4
  - jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
 
 
5
  - DrNicefellow/Qwen2.5-7B-O1-Journey-1
6
+ - bunnycore/Qwen2.5-7B-CyberRombos
7
+ - C10X/CoT-2.5
8
+ - Qwen/Qwen2.5-7B-Instruct
9
+ - Kaballas/TLetsgo
10
  library_name: transformers
11
  tags:
12
  - mergekit
 
20
  ## Merge Details
21
  ### Merge Method
22
 
23
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base.
24
 
25
  ### Models Merged
26
 
27
  The following models were included in the merge:
28
+ * [djuna/Q2.5-Fuppavy-7B](https://huggingface.co/djuna/Q2.5-Fuppavy-7B)
29
  * [jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7)
 
30
  * [DrNicefellow/Qwen2.5-7B-O1-Journey-1](https://huggingface.co/DrNicefellow/Qwen2.5-7B-O1-Journey-1)
31
+ * [bunnycore/Qwen2.5-7B-CyberRombos](https://huggingface.co/bunnycore/Qwen2.5-7B-CyberRombos)
32
+ * [C10X/CoT-2.5](https://huggingface.co/C10X/CoT-2.5)
33
+ * [Kaballas/TLetsgo](https://huggingface.co/Kaballas/TLetsgo)
34
 
35
  ### Configuration
36
 
 
42
  - model: C10X/CoT-2.5
43
  - model: bunnycore/Qwen2.5-7B-CyberRombos
44
  - model: djuna/Q2.5-Fuppavy-7B
45
+ - model: Kaballas/TLetsgo
46
  - model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
47
 
48
  merge_method: model_stock
49
+ base_model: Qwen/Qwen2.5-7B-Instruct
50
  dtype: bfloat16
51
  ```
config.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "_name_or_path": "Kaballas/TLetsgo",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
  "hidden_act": "silu",
10
  "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 18944,
13
- "max_position_embeddings": 131072,
14
  "max_window_layers": 28,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 28,
@@ -24,7 +24,6 @@
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.2",
26
  "use_cache": true,
27
- "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
30
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
  "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
  "max_window_layers": 28,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 28,
 
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.2",
26
  "use_cache": true,
 
27
  "use_sliding_window": false,
28
  "vocab_size": 152064
29
  }
mergekit_config.yml CHANGED
@@ -3,8 +3,9 @@ models:
3
  - model: C10X/CoT-2.5
4
  - model: bunnycore/Qwen2.5-7B-CyberRombos
5
  - model: djuna/Q2.5-Fuppavy-7B
 
6
  - model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
7
 
8
  merge_method: model_stock
9
- base_model: Kaballas/TLetsgo
10
  dtype: bfloat16
 
3
  - model: C10X/CoT-2.5
4
  - model: bunnycore/Qwen2.5-7B-CyberRombos
5
  - model: djuna/Q2.5-Fuppavy-7B
6
+ - model: Kaballas/TLetsgo
7
  - model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.7
8
 
9
  merge_method: model_stock
10
+ base_model: Qwen/Qwen2.5-7B-Instruct
11
  dtype: bfloat16
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b643f7436ff370b5d620617dba889de4feadcfebe98e21b107ee0951045f402
3
  size 4970993048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d696e89696ac21a4b884427b3a4b1e9e98bc48dcae19d0dae88468773010ee1
3
  size 4970993048
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44755007c88fc68ee8c1e7f5fdd0c423acab5abbe6142b322c1a62e5b8ecce96
3
  size 4932751032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b57b423518da5f5a67cadd606b1138c137139aa8d703926d74183893e45582
3
  size 4932751032
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dba961e5ddc6e54975d84428252d6d60096d7598f6bbd2974b9cc2e76ee55be
3
  size 4991495808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e968ebd978b80bec99c1e74c6b6ad77bc7e3a2b25a4575e7936ecf3d4e6c2b13
3
  size 4991495808
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:754b507473095a88fb56cbaab508bebde894df0bb83d6ffaa2f09a8698e16f05
3
  size 330326240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d59bdfb5141496b09f7aa10bf0d976a0d3aabbdf9c0a997fe7bbb627e352b03
3
  size 330326240
special_tokens_map.json CHANGED
@@ -15,7 +15,7 @@
15
  "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
- "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
15
  "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
+ "content": "<|im_end|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -195,9 +195,9 @@
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
- "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
- "eos_token": "<|endoftext|>",
201
  "errors": "replace",
202
  "model_max_length": 131072,
203
  "pad_token": "<|endoftext|>",
 
195
  "<|video_pad|>"
196
  ],
197
  "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
  "errors": "replace",
202
  "model_max_length": 131072,
203
  "pad_token": "<|endoftext|>",