Initial Lean SFT adapters (DeepSeek-Prover-V1) on gpt-oss-20b

README.md

@@ -1,17 +1,24 @@
 ---
 base_model: deepseek-ai/DeepSeek-V2-Lite
+datasets: deepseek-ai/DeepSeek-Prover-V1
 library_name: transformers
 model_name: DeepSeek-V2-Lite-Chat-deepseek-prover
 tags:
 - generated_from_trainer
+- lean4
 - sft
 - trl
+- text-generation
+- peft
+- moe
+- proof
+- lora
 licence: license
 ---
 
 # Model Card for DeepSeek-V2-Lite-Chat-deepseek-prover
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) on the [deepseek-ai/DeepSeek-Prover-V1](https://huggingface.co/datasets/deepseek-ai/DeepSeek-Prover-V1) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start