Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: microsoft/Phi-3-mini-4k-instruct
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
 library_name: peft
 ---
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "down_proj",
-    "o_proj",
-    "qkv_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fcde06120fab5bc5b040fe4ba3135f571ac311a94beed130072c4c37695566
-size 805341552
+oid sha256:cd278200eeb184394d9ce9287c9071df2ccb2d6f2e2d9d6c5ecfb954eb569f1a
+size 161495976

special_tokens_map.json

@@ -1,27 +1,20 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<｜begin▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,131 +1,194 @@
 {
-  "add_bos_token": false,
+  "add_bos_token": true,
   "add_eos_token": false,
   "add_prefix_space": null,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<｜User｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<｜Assistant｜>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32000": {
-      "content": "<|endoftext|>",
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|assistant|>",
+    "151647": {
+      "content": "<|EOT|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32002": {
-      "content": "<|placeholder1|>",
+    "151648": {
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32003": {
-      "content": "<|placeholder2|>",
+    "151649": {
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32004": {
-      "content": "<|placeholder3|>",
+    "151650": {
+      "content": "<|quad_start|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32005": {
-      "content": "<|placeholder4|>",
+    "151651": {
+      "content": "<|quad_end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32006": {
-      "content": "<|system|>",
+    "151652": {
+      "content": "<|vision_start|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32007": {
-      "content": "<|end|>",
+    "151653": {
+      "content": "<|vision_end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32008": {
-      "content": "<|placeholder5|>",
+    "151654": {
+      "content": "<|vision_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32009": {
-      "content": "<|placeholder6|>",
+    "151655": {
+      "content": "<|image_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32010": {
-      "content": "<|user|>",
+    "151656": {
+      "content": "<|video_pad|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "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｜>'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "legacy": false,
-  "model_max_length": 4096,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "left",
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": null,
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941d374ce7d8e155ca8227b13f4e11c183b4cc61f84cb675ab94f50ea680500e
+oid sha256:2c4cf38de666ae5aa2fb7249d8573b92d9b36d3b54619dfccbbe531c2b02bbcd
 size 5432