valerielucro
/

mistral_gsm8k_dpo_cot_r64

Inference Endpoints

Model card Files Files and versions Community

mistral_gsm8k_dpo_cot_r64 / tokenizer.json

valerielucro's picture

rank 64 adapter trained with DPO on the gsm8k preference dataset with cot and 1 epoch

b5f33c8 verified 5 months ago

history contribute delete

1.8 MB

File too large to display, you can check the raw version instead.