RichardErkhov/mistral-community_-_Mistral-7B-v0.2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-v0.2 - GGUF

• Model creator: https://huggingface.co/mistral-community/
• Original model: https://huggingface.co/mistral-community/Mistral-7B-v0.2/

Name	Quant method	Size
Mistral-7B-v0.2.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-v0.2.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-v0.2.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-v0.2.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-v0.2.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-v0.2.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-v0.2.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-v0.2.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-v0.2.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-v0.2.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-v0.2.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-v0.2.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-v0.2.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-v0.2.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-v0.2.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-v0.2.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-v0.2.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-v0.2.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-v0.2.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-v0.2.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-v0.2.Q6_K.gguf	Q6_K	5.53GB

Original model description:

license: apache-2.0

Conversion process:

1. Download original weights from https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar
2. Convert with https://github.com/huggingface/transformers/blob/main/src/transformers/models/mistral/convert_mistral_weights_to_hf.py
3. You may need to copy the tokenizer.model from Mistral-7B-Instruct-v0.2 repo.