model updated

README.md

@@ -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

@@ -20,7 +20,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.1",
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "vocab_size": 32768
 }

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": [
     2
   ],
-  "transformers_version": "4.56.1"
+  "transformers_version": "4.56.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d434833acd2e102e39a336b6a1037b1cce9e71237acbc1b3d0f600f5e7bfb78c
+oid sha256:10a9c496791786f25c381d4986e172a3f251e8977dd787bb2d42ba756268bb17
 size 4949453792

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ff44833d2fee7b4378e44b11ed5df0ee6c0e1bf3ebead3345b2c3f55cf6279
+oid sha256:280784ff68f54b4950399c2b13bed440fcd98e1225374f6a0a98c0561a2e1ea4
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70be310868b2fed5b49c052d42762238be67840eb52dcce09c70752688da3581
+oid sha256:945ce82bc7c762414a68b1ad86a8d99c0df333055dbe574bb8b601beae38d2dd
 size 4546807800

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c93f88589e783be28e8579f08d18ac05cf738a5aadcf97e4ffd043583e6a92
+oid sha256:06ce0177620c66172b44bb8dd7ebca918df39e3f083b2d45d75645c17b2c2a56
 size 6801