Merge remote-tracking branch 'origin' into pr/2

README.md

@@ -2,14 +2,14 @@
 language:
 - ru
 ---
-# T-lite-instruct-1.0
+# T-lite-it-1.0
 
 **🚨 T-lite is designed for further fine-tuning and is not intended as a ready-to-use conversational assistant. Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.**
 
 
 ## Description
 
-T-lite-instruct-0.1 was trained in bf16. 
+T-lite-it-0.1 was trained in bf16. 
 
 Detailed model card’s coming soon…
 
@@ -20,7 +20,7 @@ Detailed model card’s coming soon…
 ## 📊 Benchmarks
 
 Detailed model card’s coming soon…
-Here we present the results of T-lite-instruct-1.0 on automatic benchmarks.
+Here we present the results of T-lite-it-1.0 on automatic benchmarks.
 
 ## 👨‍💻 Examples of usage
 

added_tokens.json

@@ -1,24 +0,0 @@
-{
-  "</tool_call>": 151658,
-  "<tool_call>": 151657,
-  "<|box_end|>": 151649,
-  "<|box_start|>": 151648,
-  "<|endoftext|>": 151643,
-  "<|file_sep|>": 151664,
-  "<|fim_middle|>": 151660,
-  "<|fim_pad|>": 151662,
-  "<|fim_prefix|>": 151659,
-  "<|fim_suffix|>": 151661,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644,
-  "<|image_pad|>": 151655,
-  "<|object_ref_end|>": 151647,
-  "<|object_ref_start|>": 151646,
-  "<|quad_end|>": 151651,
-  "<|quad_start|>": 151650,
-  "<|repo_name|>": 151663,
-  "<|video_pad|>": 151656,
-  "<|vision_end|>": 151653,
-  "<|vision_pad|>": 151654,
-  "<|vision_start|>": 151652
-}

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/from_s3/model",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

generation_config.json

@@ -1,6 +1,14 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 70,
   "transformers_version": "4.46.2"
-}
+}

special_tokens_map.json

@@ -1,31 +0,0 @@
-{
-  "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|>"
-  ],
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer_config.json

@@ -197,7 +197,7 @@
   "bos_token": null,
   "chat_template": "{% for message in messages %}\n    {{- '<|im_start|>' + message.role + '\n' + message.content  + '<|im_end|>' + '\n' -}}\n{% endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' -}}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
   "errors": "replace",
   "model_max_length": 8192,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8bac43683e08677189ad196b17c90e3c619d4d4929e3f8f6483d571c8ebca8ed
-size 7608