Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: TianshengHuang/s1k
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
 library_name: transformers
 model_name: _sft_sft_5
 tags:
@@ -11,7 +11,7 @@ licence: license
 
 # Model Card for _sft_sft_5
 
-This model is a fine-tuned version of [TianshengHuang/s1k](https://huggingface.co/TianshengHuang/s1k).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -1,22 +1,22 @@
 {
-  "_name_or_path": "TianshengHuang/s1k",
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 27648,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 70,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
   "model_type": "qwen2",
   "num_attention_heads": 40,
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,

generation_config.json

@@ -1,14 +1,9 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 151646,
   "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,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
   "transformers_version": "4.46.1"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d797f70ba7f1b3fb4a2c971d77896c59369c7d634c09701ff321374ecba4eaa
+oid sha256:32b302cbcf810efef02f1f796b7b429b647bb46dbfe27bdd0794e323c25d06d5
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261b71b88deead7ac53233764a6055ab10165cb6b5aed7391cce1f52ea128834
+oid sha256:2f31635e59a73214edaa09c3ae3f16d9a042ef61dc366dd47a80a1286b93df31
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f852efdb550af10f4e743411354a7e7d8f7af855bcc496c0a75d249a0b8b052
+oid sha256:51941ae259a3458153c01d69ca44c7ecb1460a6dda0c8585807256101695a35a
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12d7185a37cff385b12e232168ca6111188d69e8e6cd297e7de4d0bda6a16ba
+oid sha256:6b8945ba7bf120acfe84403c65126947a6fd3701f5f1d4df17b25708d8050e9f
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90c43faf7910d1659af1fceb42cbbe6bc4f8ae68b68543b427e01177a9311e2
+oid sha256:5c4fcf1f208159793a48fa86a00081b1e48ce5daa4c346bb5012f8482a5b067e
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cedbe456c2053e1f7fb2c7be6f1bde928131cacd68120bca2b07e3beb8a75718
+oid sha256:05858e15319a18ac9fbf89244c860817a71de9dc81841a9388ea8ec53693fd05
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa920f188ec3a93741ffcb5f3d63970a5031d78e9c4ef7bf4b1f3a521370a72
+oid sha256:9166ef18fb3d2ca8b8a89f2e53965a1d47fe26a586e8b53427b9677351f9c6d5
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814d660f09932fbcdee9f13b97836e5d471ad3e6d61ad85e4439af43edb9b831
+oid sha256:f822daacd802e02d78ecdded1777e3ee30142ee12ddff14f1b873ffd7480f651
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b0af36cfcea91335b526ffb69f37918d7d0f1d92bb0ac4b31c0067dd93a8ec
+oid sha256:8d8fc34ad71b574d5bd25815dc2441feb93d7e2c9bba1bb8b0f50960ef35da0a
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2cdb588e227b7a4cba9853e9338c0040471fcd1c59ab50b4c10161e3a43bc2a
+oid sha256:4cf064c509eba81e2d252637d7c787d0239244976c4f4e6c1d856b9407abd585
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495a2e6daaca88b15caae5b3113ebf2ee873dd605c345212b0a050ae4f6ed5df
+oid sha256:3fff6dfb64bbe5e722a5d19ae3242d55e367b973dc0239318adce6d5162b4435
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4faa71b9f19c4d695e19e005d8965f0602fbf9ef51d85fb51b1ae62f4d595a7
+oid sha256:8b4cf1d664a5cad0d453eeb5d9d909856b465c63d843f9d1d5884b795faca590
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119d87ff5a65fe3c3ee4b49cc58ebca44b9e70bde8ec4d3db5c4b5bd2c11f7cc
+oid sha256:08874d84adb319f3acff090b4258571e770687d460212d7d8a884bbe7b1e7437
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa6be68455fa0c1569a8e0519dac90b7f5dcfe274b6c6f67ea928f54e32a1bd
+oid sha256:22d385ce64bdfbc0406a62120b7455bb08fa45e768b05c8c7dfbfb37aae421bb
 size 2123397800

special_tokens_map.json

@@ -1,28 +1,20 @@
 {
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68301b5308a972f0c3e44b7251787e603564d598575dab87d8068b0ef893996d
-size 11421996
+oid sha256:8749954a732f5b46cd497790be3031e5199a8f6e7f72862d5e1d26513bac9564
+size 11422878

tokenizer_config.json

@@ -1,9 +1,10 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "151643": {
-      "content": "<|endoftext|>",
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,23 +12,23 @@
       "special": true
     },
     "151644": {
-      "content": "<|im_start|>",
+      "content": "<｜User｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151645": {
-      "content": "<|im_end|>",
+      "content": "<｜Assistant｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151646": {
-      "content": "<|object_ref_start|>",
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -35,28 +36,28 @@
       "special": true
     },
     "151647": {
-      "content": "<|object_ref_end|>",
+      "content": "<|EOT|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151648": {
-      "content": "<|box_start|>",
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151649": {
-      "content": "<|box_end|>",
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "151650": {
       "content": "<|quad_start|>",
@@ -179,34 +180,15 @@
       "special": false
     }
   },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>",
-    "<|object_ref_start|>",
-    "<|object_ref_end|>",
-    "<|box_start|>",
-    "<|box_end|>",
-    "<|quad_start|>",
-    "<|quad_end|>",
-    "<|vision_start|>",
-    "<|vision_end|>",
-    "<|vision_pad|>",
-    "<|image_pad|>",
-    "<|video_pad|>"
-  ],
-  "bos_token": null,
-  "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",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "max_length": 20000,
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "stride": 0,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": null
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9836d5824aaeeca875e0b2e9d5fdb7e9ac54ca2961f3c5cbe0f2cdbc25bb45
-size 5752
+oid sha256:93df8358164e9e3490f9367d2a961f98b3c4b9c4f5470d9c7e3baf8d22f17975
+size 5816