model updated

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: QwenModel_dpo
 tags:
 - generated_from_trainer
-- dpo
 - trl
+- dpo
 licence: license
 ---
 
@@ -35,10 +35,10 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 ### Framework versions
 
 - TRL: 0.23.0
-- Transformers: 4.56.1
+- Transformers: 4.56.2
 - Pytorch: 2.8.0.dev20250319+cu128
 - Datasets: 4.1.1
-- Tokenizers: 0.22.0
+- Tokenizers: 0.22.1
 
 ## Citations
 

config.json

@@ -51,7 +51,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.1",
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.56.1"
+  "transformers_version": "4.56.2"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b5f36e5c538c00a414ab69e74b700d0fb9241c1973a18125c89d19d7df9b3c
+oid sha256:adc6d07800dbb954f5ee36b7257cbc2a2aa526161b8940cd818cec0920b3369d
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41fcfca9a56b6a7ad97f5edec9659d38d6b764520ad8cb405405dcb469b2b0a
+oid sha256:b49f291cf1ca115dcb845b8f293aaeda0001486cf56fcf75eaa5559c50d34d0a
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1380dce938198543506c39ef9445fee48030877ff39023c99133832e9804859
+oid sha256:2d16e5c4f0e0ebd005dda6ec5ccee73510662e7145ec6c1699eed1045e7ccbec
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd70e777116decbccca81e84c28955490f3c9c2817c9f61e0c21de09efae97eb
+oid sha256:62b045376cd6363b450a3bc3d37c90942f8c226f3fd60c4d660521c132b97b32
 size 1089994880

special_tokens_map.json

@@ -21,11 +21,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|im_end|>"
 }

tokenizer_config.json

@@ -200,7 +200,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe6254b4b821c430481204db5415dedc784d6dad7cf725a918df7e847d0f1a6
+oid sha256:12122b9fdc78225f20c28a9cffc0e46a45aa91a2facc7e5e3735f047f27247a4
 size 6801