모델 업데이트

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "\"UNIVA-Bllossom/DeepSeek-llama3.1-Bllossom-8",
+  "_name_or_path": "/home/raid/models/24UNSPC_Tulkun_v3.0.4/",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -29,8 +29,8 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
   "use_cache": false,
-  "vocab_size": 128257
+  "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.48.3"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43aeb40dea39d1879925512c47c4e96047a5d7b92f50dc994872e441f97aab5b
-size 4976706864
+oid sha256:939bc0a77e349a9896e2374abcb481ed147b042c49dc0b527339d967f01a2fd1
+size 4976698592

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c99f508a7870d7036720338601b1b6e991296b88594366c6fa9c606c7c1a76
-size 4999802720
+oid sha256:e9eca7f9936d35bc42c01038d26ff89bd26fab8b79a093c6aa19deb66ec851e5
+size 4999802616

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c80b287c1541e2bb9fa18ef82751a0b82f9d6560f2945fb56b6ef9ca7b2eb27
-size 4915916176
+oid sha256:f0d23c52ce9197c04995fc64682e120e4ec47bbe0cf03c6d7c576b7efa3f2058
+size 4915916080

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66973340e2b2c962618eb6db28a820442d1829e9e473eb819d56d2d9430cec8
-size 1168147000
+oid sha256:1e318aacfeffb95c600b62f1d9a224f9ada79f365b7746d5449363e0d81abc64
+size 1168138808

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16060538880
+    "total_size": 16060522496
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|end_of_text|>",
+    "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 sha256:16f2ebc8d9a7de55360d83ea69f97916a1389f0a72264664d4d6c4db6da8d0b8
-size 17209722
+oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
+size 17209530

tokenizer_config.json

@@ -2050,24 +2050,16 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "128256": {
-      "content": "<|end_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<｜begin▁of▁sentence｜>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "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": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
   "legacy": true,
   "model_max_length": 16384,
-  "pad_token": "<|end_of_text|>",
+  "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": null,