danielhanchen commited on
Commit
e25cd85
·
verified ·
1 Parent(s): 0ba75db

Add files using upload-large-folder tool

Browse files
config.json CHANGED
@@ -4,6 +4,7 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
7
  "eos_token_id": 151645,
8
  "head_dim": 128,
9
  "hidden_act": "silu",
@@ -16,16 +17,14 @@
16
  "num_attention_heads": 64,
17
  "num_hidden_layers": 64,
18
  "num_key_value_heads": 8,
19
- "pad_token_id": 151654,
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
22
  "rope_theta": 1000000,
23
  "sliding_window": null,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.52.0.dev0",
27
- "unsloth_fixed": true,
28
  "use_cache": true,
29
  "use_sliding_window": false,
30
  "vocab_size": 151936
31
- }
 
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
 
17
  "num_attention_heads": 64,
18
  "num_hidden_layers": 64,
19
  "num_key_value_heads": 8,
 
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
22
  "rope_theta": 1000000,
23
  "sliding_window": null,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.0",
 
27
  "use_cache": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
+ }
generation_config.json CHANGED
@@ -1,14 +1,13 @@
1
  {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "max_length": 40960,
9
- "pad_token_id": 151654,
10
- "temperature": 0.6,
11
- "top_k": 20,
12
- "top_p": 0.95,
13
- "transformers_version": "4.52.0.dev0"
14
- }
 
1
  {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.51.0"
13
+ }
 
model-00001-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52562b2ff97b61764260273e71bf5b4cf8a66f569399398f26dec0300fcf1316
3
+ size 3957109648
model-00002-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26764b2c6878e3fb7198895fa833ec62838d84a19665e6abfbae43c6daf02b3
3
+ size 3900791760
model-00003-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5ba7bed9c52bc121e75cbe8a7be46936d0006cc80f42a6d5886ed40b4c2a62
3
+ size 3900791760
model-00004-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f736f6ac4d8c30866107fb1185a05b3c3cfce9717720082f466fa44e691bcec8
3
+ size 3900791800
model-00005-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52ed375c083209c54d42ac510afeb1fbb5af4f193be2dc7d103f665a0f212d3
3
+ size 3900791800
model-00006-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37fae28990b0e4a70228549d040c0393e87bee3820d59e58e47844974d8dff5b
3
+ size 3900791800
model-00007-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37776006aeaba29eca8bc73b2b963fe3477e1c2e3f6a27cb9527be75b905e1bf
3
+ size 3900791800
model-00008-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e74e9129674fe330948005075d70ab4fa0b92b68fb220c5a693f9cea553730
3
+ size 3900791800
model-00009-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a044b3602a01bd8ea62ff51badf9cc038ab1d73d97399480e6a55b4c86fa7fa6
3
+ size 3900791800
model-00010-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9966612ba7ecfc2cd2e592fb95224b86d743271ff88e172cc272a4b26382aa75
3
+ size 3900791800
model-00011-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a058a0ac7d4b992b731c29221ecfb4b76b8a48d9004d0e8a62ba44f699845c
3
+ size 3900791800
model-00012-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a1aa89093fea07325f787072a468e3482a470ff4b7fe5ead5f749683907c40
3
+ size 3900791800
model-00013-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f3381bab31a23370c37d922290aeecdf603418336058fb86fe42d8f51ac40c
3
+ size 3900791800
model-00014-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8713b062ddc178acf5917610b7f4b64eede833b2ea4aa37bd562dcf2f3a3339d
3
+ size 3900791800
model-00015-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec439d23931821a236d8f62fa79deecf5551bd25602278aa2ae0ce432b378cf
3
+ size 3900791800
model-00016-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e569139fadd61fe7c8f9eb1c976d9a627cae48c57ddf228cfbd0593c59c64ff7
3
+ size 3900791800
model-00017-of-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f47c318fcd7797c0f85b4233cb754438b10e795b8bc874889090c416a94bd38
3
+ size 3055341992
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -227,14 +227,13 @@
227
  "<|video_pad|>"
228
  ],
229
  "bos_token": null,
 
230
  "clean_up_tokenization_spaces": false,
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 40960,
235
- "pad_token": "<|vision_pad|>",
236
- "padding_side": "left",
237
  "split_special_tokens": false,
238
  "tokenizer_class": "Qwen2Tokenizer",
239
  "unk_token": null
240
- }
 
227
  "<|video_pad|>"
228
  ],
229
  "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
231
  "clean_up_tokenization_spaces": false,
232
  "eos_token": "<|im_end|>",
233
  "errors": "replace",
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
 
 
236
  "split_special_tokens": false,
237
  "tokenizer_class": "Qwen2Tokenizer",
238
  "unk_token": null
239
+ }