Modelpublic

sayhan/Mixtral-8x7B-v0.1-turkish-GGUF

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

3likes506downloads

Model Card

Mixtral 8x7B v0.1 Turkish

—Model creator: malhajar
—Original model: Mixtral-8x7B-v0.1-turkish

Description

This repo contains GGUF format model files for malhajar's Mixtral 8x7B v0.1 Turkish

Original model

—Developed by: `Mohamad Alhajar`
—Language(s) (NLP): Turkish
—Finetuned from model: `mistralai/Mistral-7B-Instruct-v0.2`

Original model description

malhajar/Mixtral-8x7B-v0.1-turkish is a finetuned version of Mixtral-8x7B-v0.1 using SFT Training. This model can answer information in turkish language as it is finetuned on a turkish dataset specifically `alpaca-gpt4-tr`

Quantizon types

quantization method	bits	size	description	recommended
Q3KS	3	20.4 GB	very small, high quality loss	❌
Q3KL	3	26.4 GB	small, substantial quality loss	❌
Q4_0	4	26.4 GB	legacy; small, very high quality loss	❌
Q4KM	4	28.4 GB	medium, balanced quality	✅
Q5_0	5	33.2 GB	legacy; medium, balanced quality	❌
Q5KS	5	32.2 GB	large, low quality loss	✅
Q5KM	5	33.2 GB	large, very low quality loss	✅
Q6_K	6	38.4 GB	very large, extremely low quality loss	❌
Q8_0	8	49.6 GB	very large, extremely low quality loss	❌

Prompt Template

### Instruction:
<prompt> (without the <>)
### Response: