Skip to content

fbaldassarri

mistralai_Mistral-7B-Instruct-v0.3-autoround-int4-gs128-asym

fbaldassarri/mistralai_Mistral-7B-Instruct-v0.3-autoround-int4-gs128-asym

mistralai_Mistral-7B-Instruct-v0.3-autoround-int4-gs128-asym is a text generation model from fbaldassarri. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

Quantized version of mistralai/Mistral-7B-v0.3-Instruct using torch.float32 for quantization tuning. - 4 bits (INT4) - group size = 128 - Asymmetrical Quantization - Method WoQ (AutoRound format)

Downloads · 30 days

7

5% of all-time downloads

All-time downloads

146

Public

Parameters

1.2B

4.7 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors4.7 GB · 100%

Parameter types

How the weights are stored.

I32880M · 73%

Try a prompt

Base models

Task
Text Generation
Type
mistral
License
apache-2.0
Languages
en, fr
Created
Jan 17, 2025
Updated
Jan 19, 2025