metadata
datasets:
- HuggingFaceH4/ultrafeedback_binarized
base_model:
- unsloth/Llama-3.2-1B-Instruct
Base model: unsloth/Llama-3.2-1B-Instruct
Tokenizer: OpenRLHF/Llama-3-8b-sft-mixture
Preference dataset: HuggingFaceH4/ultrafeedback_binarized