RichardErkhov/jhflow_-_mistral7b-lora-multiturn-v4-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral7b-lora-multiturn-v4 - GGUF

• Model creator: https://huggingface.co/jhflow/
• Original model: https://huggingface.co/jhflow/mistral7b-lora-multiturn-v4/

Name	Quant method	Size
mistral7b-lora-multiturn-v4.Q2_K.gguf	Q2_K	2.53GB
mistral7b-lora-multiturn-v4.IQ3_XS.gguf	IQ3_XS	2.81GB
mistral7b-lora-multiturn-v4.IQ3_S.gguf	IQ3_S	2.96GB
mistral7b-lora-multiturn-v4.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral7b-lora-multiturn-v4.IQ3_M.gguf	IQ3_M	3.06GB
mistral7b-lora-multiturn-v4.Q3_K.gguf	Q3_K	3.28GB
mistral7b-lora-multiturn-v4.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral7b-lora-multiturn-v4.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral7b-lora-multiturn-v4.IQ4_XS.gguf	IQ4_XS	3.67GB
mistral7b-lora-multiturn-v4.Q4_0.gguf	Q4_0	3.83GB
mistral7b-lora-multiturn-v4.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral7b-lora-multiturn-v4.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral7b-lora-multiturn-v4.Q4_K.gguf	Q4_K	4.07GB
mistral7b-lora-multiturn-v4.Q4_K_M.gguf	Q4_K_M	4.07GB
mistral7b-lora-multiturn-v4.Q4_1.gguf	Q4_1	4.24GB
mistral7b-lora-multiturn-v4.Q5_0.gguf	Q5_0	4.65GB
mistral7b-lora-multiturn-v4.Q5_K_S.gguf	Q5_K_S	4.65GB
mistral7b-lora-multiturn-v4.Q5_K.gguf	Q5_K	4.78GB
mistral7b-lora-multiturn-v4.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral7b-lora-multiturn-v4.Q5_1.gguf	Q5_1	5.07GB
mistral7b-lora-multiturn-v4.Q6_K.gguf	Q6_K	5.53GB
mistral7b-lora-multiturn-v4.Q8_0.gguf	Q8_0	7.17GB

Original model description:

• Original Model : maywell/Synatra-7B-v0.3-dpo
• Prompt format : ChatML (same as the original model)