README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

PiVoT-10.7B-Mistral-v0.2 - GGUF

• Model creator: https://huggingface.co/maywell/
• Original model: https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2/

Name	Quant method	Size
PiVoT-10.7B-Mistral-v0.2.Q2_K.gguf	Q2_K	3.73GB
PiVoT-10.7B-Mistral-v0.2.IQ3_XS.gguf	IQ3_XS	4.14GB
PiVoT-10.7B-Mistral-v0.2.IQ3_S.gguf	IQ3_S	4.37GB
PiVoT-10.7B-Mistral-v0.2.Q3_K_S.gguf	Q3_K_S	4.34GB
PiVoT-10.7B-Mistral-v0.2.IQ3_M.gguf	IQ3_M	4.51GB
PiVoT-10.7B-Mistral-v0.2.Q3_K.gguf	Q3_K	4.84GB
PiVoT-10.7B-Mistral-v0.2.Q3_K_M.gguf	Q3_K_M	4.84GB
PiVoT-10.7B-Mistral-v0.2.Q3_K_L.gguf	Q3_K_L	5.26GB
PiVoT-10.7B-Mistral-v0.2.IQ4_XS.gguf	IQ4_XS	5.43GB
PiVoT-10.7B-Mistral-v0.2.Q4_0.gguf	Q4_0	5.66GB
PiVoT-10.7B-Mistral-v0.2.IQ4_NL.gguf	IQ4_NL	5.72GB
PiVoT-10.7B-Mistral-v0.2.Q4_K_S.gguf	Q4_K_S	5.7GB
PiVoT-10.7B-Mistral-v0.2.Q4_K.gguf	Q4_K	6.02GB
PiVoT-10.7B-Mistral-v0.2.Q4_K_M.gguf	Q4_K_M	6.02GB
PiVoT-10.7B-Mistral-v0.2.Q4_1.gguf	Q4_1	6.27GB
PiVoT-10.7B-Mistral-v0.2.Q5_0.gguf	Q5_0	6.89GB
PiVoT-10.7B-Mistral-v0.2.Q5_K_S.gguf	Q5_K_S	6.89GB
PiVoT-10.7B-Mistral-v0.2.Q5_K.gguf	Q5_K	7.08GB
PiVoT-10.7B-Mistral-v0.2.Q5_K_M.gguf	Q5_K_M	7.08GB
PiVoT-10.7B-Mistral-v0.2.Q5_1.gguf	Q5_1	7.51GB
PiVoT-10.7B-Mistral-v0.2.Q6_K.gguf	Q6_K	8.2GB
PiVoT-10.7B-Mistral-v0.2.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: cc-by-sa-4.0 language: - en - ko pipeline_tag: text-generation

PiVoT-10.7B-Mistral-v0.2

Model Details

Description

PivoT is Finetuned model based on merge of Mistral 0.2.

SFT + DPO used when training.

Follow me on twitter: https://twitter.com/stablefluffy

Consider Support me making these model alone: https://www.buymeacoffee.com/mwell or with Runpod Credit Gift 💕

Contact me on Telegram: https://t.me/AlzarTakkarsen