Upload folder using huggingface_hub (#5)

- b25ac73db3e0e71bbf38c2a5e7ed02cffd88039f534a5c32beca76297058f4ae (77f69b816abb8017f0ed05a0d3383a6ebfeeb043)
- d197f0d01addb5adabd46d0b41996cb6d393776f22b6bd7e91148bce654bf2d9 (d69f30aa30db7700cac10a42bdd59514cf1a1313)
- 3aff618fc084c047c37e55c56b78e9e422c36e9db59c1fb5e0877d5c03f46f76 (1172fc9e384e4ee65ebb27a0ac385a4b0c2f8431)

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-3B",
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 32768,
-  "max_window_layers": 36,
+  "max_window_layers": 70,
   "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
@@ -24,7 +24,6 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_cache": true,
-  "use_mrope": false,
   "use_sliding_window": false,
-  "vocab_size": 151665
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,6 +1,14 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.45.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ffc42b32cd02cae2c31c0333684a92ab28db1b20a905b4fdf20dca6acc42c7
-size 4981425104
+oid sha256:f64ede8105bca615e7e0a3167b1c0a5352ecdcbfd9b8a2764d139c497495f2fc
+size 4982535120

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be77b22c410829154989b5c8cb9f815e097ceff682afa0f3fe74d0178712fe1
+oid sha256:8baaa295921e0e2e32894fcf307a30f2da2fe38065b6cd773d002292f44978bd
 size 4920168312

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8982a3223d5734d499530cbc35e6b3d28c4cb1983fc4ea73b80ebc41422ff553
+oid sha256:e754184c6cd33f0cf6edc6386cbec2b000c295527bd66e809fba64a4fc35fbff
 size 1138810568

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 11040354304
+    "total_size": 11041464320
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",

tokenizer_config.json

@@ -195,7 +195,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "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",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",