RichardErkhov/ministral_-_Ministral-3b-instruct-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Ministral-3b-instruct - GGUF

• Model creator: https://huggingface.co/ministral/
• Original model: https://huggingface.co/ministral/Ministral-3b-instruct/

Name	Quant method	Size
Ministral-3b-instruct.Q2_K.gguf	Q2_K	1.19GB
Ministral-3b-instruct.IQ3_XS.gguf	IQ3_XS	1.31GB
Ministral-3b-instruct.IQ3_S.gguf	IQ3_S	1.38GB
Ministral-3b-instruct.Q3_K_S.gguf	Q3_K_S	1.38GB
Ministral-3b-instruct.IQ3_M.gguf	IQ3_M	1.42GB
Ministral-3b-instruct.Q3_K.gguf	Q3_K	1.51GB
Ministral-3b-instruct.Q3_K_M.gguf	Q3_K_M	1.51GB
Ministral-3b-instruct.Q3_K_L.gguf	Q3_K_L	1.64GB
Ministral-3b-instruct.IQ4_XS.gguf	IQ4_XS	1.69GB
Ministral-3b-instruct.Q4_0.gguf	Q4_0	1.77GB
Ministral-3b-instruct.IQ4_NL.gguf	IQ4_NL	1.78GB
Ministral-3b-instruct.Q4_K_S.gguf	Q4_K_S	1.78GB
Ministral-3b-instruct.Q4_K.gguf	Q4_K	1.86GB
Ministral-3b-instruct.Q4_K_M.gguf	Q4_K_M	1.86GB
Ministral-3b-instruct.Q4_1.gguf	Q4_1	1.95GB
Ministral-3b-instruct.Q5_0.gguf	Q5_0	2.14GB
Ministral-3b-instruct.Q5_K_S.gguf	Q5_K_S	2.14GB
Ministral-3b-instruct.Q5_K.gguf	Q5_K	2.19GB
Ministral-3b-instruct.Q5_K_M.gguf	Q5_K_M	2.19GB
Ministral-3b-instruct.Q5_1.gguf	Q5_1	2.33GB
Ministral-3b-instruct.Q6_K.gguf	Q6_K	2.53GB
Ministral-3b-instruct.Q8_0.gguf	Q8_0	3.28GB

Original model description:

library_name: transformers inference: parameters: temperature: 1 top_p: 0.95 top_k: 40 repetition_penalty: 1.2 license: apache-2.0 language: - en pipeline_tag: text-generation

Model Description

Ministral is a series of language model, build with same architecture as the famous Mistral model, but with less size.

• Model type: A 3B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
• Language(s) (NLP): Primarily English
• License: Apache 2.0
• Finetuned from model: mistralai/Mistral-7B-v0.1