End of training

README.md

@@ -1,8 +1,10 @@
 ---
+datasets: LuyiCui/numina-deepseek-r1-qwen-7b-efficient-2-preference
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-DPO-2
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - dpo
 licence: license
@@ -10,7 +12,7 @@ licence: license
 
 # Model Card for DeepSeek-R1-Distill-Qwen-1.5B-DPO-2
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [LuyiCui/numina-deepseek-r1-qwen-7b-efficient-2-preference](https://huggingface.co/datasets/LuyiCui/numina-deepseek-r1-qwen-7b-efficient-2-preference) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936