End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
+datasets: AI-MO/NuminaMath-TIR
 library_name: transformers
 model_name: deepseek-v2-lite-16b-chat-R1-Distill-batch8-numinamath
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for deepseek-v2-lite-16b-chat-R1-Distill-batch8-numinamath
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -55,7 +55,7 @@
   "topk_method": "greedy",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 102400
 }