solidrust
/

flammen17-py-DPO-v1-7B-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

nbeerbower/flammen17-py-DPO-v1-7B AWQ

Model creator: nbeerbower
Original model: flammen17-py-DPO-v1-7B

Model Summary

A Mistral 7B LLM built from merging pretrained models and finetuning on Jon Durbin's py-dpo-v0.1.

Finetuned using an A100 on Google Colab. 🙏

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

Downloads last month: 9

Safetensors

Model size

1.2B params

Tensor type

I32

·

FP16

·

Inference Examples

Text Generation

Inference API (serverless) has been turned off for this model.

Model tree for solidrust/flammen17-py-DPO-v1-7B-AWQ

Base model

flammenai/flammen17-mistral-7B

Finetuned

nbeerbower/flammen17-py-DPO-v1-7B

Quantized

(2)

this model

Dataset used to train solidrust/flammen17-py-DPO-v1-7B-AWQ

Collection including solidrust/flammen17-py-DPO-v1-7B-AWQ

7B AWQ

These models are selected for their compatibility with small 12GB memory GPUs. • 204 items • Updated Sep 3 • 2