solidrust
/

bophades-mistral-math-DPO-7B-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

nbeerbower/bophades-mistral-math-DPO-7B AWQ

Model creator: nbeerbower
Original model: bophades-mistral-math-DPO-7B

Model Summary

bophades-v2-mistral-7B finetuned on kyujinpy/orca_math_dpo.

Finetuned using an A100 on Google Colab. 🙏

Fine-tune a Mistral-7b model with Direct Preference Optimization - Maxime Labonne

Downloads last month: 2

Safetensors

Model size

1.2B params

Tensor type

I32

·

FP16

·

Quantized from

Dataset used to train solidrust/bophades-mistral-math-DPO-7B-AWQ

Collection including solidrust/bophades-mistral-math-DPO-7B-AWQ

7B AWQ

These models are selected for their compatibility with small 12GB memory GPUs. • 154 items • Updated 11 days ago • 2