Quantization made by Richard Erkhov.

flammen19X-mistral-7B - GGUF

Model creator: https://huggingface.co/flammenai/
Original model: https://huggingface.co/flammenai/flammen19X-mistral-7B/

Name	Quant method	Size
flammen19X-mistral-7B.Q2_K.gguf	Q2_K	2.53GB
flammen19X-mistral-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
flammen19X-mistral-7B.IQ3_S.gguf	IQ3_S	2.96GB
flammen19X-mistral-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
flammen19X-mistral-7B.IQ3_M.gguf	IQ3_M	3.06GB
flammen19X-mistral-7B.Q3_K.gguf	Q3_K	3.28GB
flammen19X-mistral-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
flammen19X-mistral-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
flammen19X-mistral-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
flammen19X-mistral-7B.Q4_0.gguf	Q4_0	3.83GB
flammen19X-mistral-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
flammen19X-mistral-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
flammen19X-mistral-7B.Q4_K.gguf	Q4_K	4.07GB
flammen19X-mistral-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
flammen19X-mistral-7B.Q4_1.gguf	Q4_1	4.24GB
flammen19X-mistral-7B.Q5_0.gguf	Q5_0	4.65GB
flammen19X-mistral-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
flammen19X-mistral-7B.Q5_K.gguf	Q5_K	4.78GB
flammen19X-mistral-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
flammen19X-mistral-7B.Q5_1.gguf	Q5_1	5.07GB
flammen19X-mistral-7B.Q6_K.gguf	Q6_K	5.53GB
flammen19X-mistral-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: - flammenai/flammen18X-mistral-7B datasets: - ResplendentAI/NSFW_RP_Format_NoQuote tags: - nsfw - not-for-all-audiences

flammen19X-mistral-7B

A Mistral 7B LLM built from merging pretrained models and finetuning on ResplendentAI/NSFW_RP_Format_NoQuote. Flammen specializes in exceptional character roleplay, creative writing, and general intelligence.

Method

Finetuned using an A100 on Google Colab.

Fine-tune Mistral-7b with SFT+TRL - Maxime Labonne