| license: mit | |
| datasets: | |
| - pr4nav101/COT_TTM_Finetuning | |
| language: | |
| - en | |
| base_model: | |
| - unsloth/Llama-3.2-1B-Instruct-bnb-4bit | |
| - pr4nav101/llama-3-8b-Instruct-bnb-4bit-Tiny-Thought-Model-Large | |
| pipeline_tag: text-generation | |
| library_name: peft | |
| tags: | |
| - COT | |
| - TTM | |
| - LLM | |
| method: | |
| - Knowledge Distillation with Reverse KL Divergence + PEFT Finetuning | |