CoolFace
Modelpublic

RichardErkhov/JCX-kcuf_-_openchat_3.5-gpt-4-80k-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes439downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

openchat_3.5-gpt-4-80k - GGUF

  • —Model creator: https://huggingface.co/JCX-kcuf/
  • —Original model: https://huggingface.co/JCX-kcuf/openchat_3.5-gpt-4-80k/
NameQuant methodSize
openchat_3.5-gpt-4-80k.Q2_K.ggufQ2_K2.53GB
openchat_3.5-gpt-4-80k.IQ3_XS.ggufIQ3_XS2.81GB
openchat_3.5-gpt-4-80k.IQ3_S.ggufIQ3_S2.96GB
openchat_3.5-gpt-4-80k.Q3_K_S.ggufQ3KS2.95GB
openchat_3.5-gpt-4-80k.IQ3_M.ggufIQ3_M3.06GB
openchat_3.5-gpt-4-80k.Q3_K.ggufQ3_K3.28GB
openchat_3.5-gpt-4-80k.Q3_K_M.ggufQ3KM3.28GB
openchat_3.5-gpt-4-80k.Q3_K_L.ggufQ3KL3.56GB
openchat_3.5-gpt-4-80k.IQ4_XS.ggufIQ4_XS3.67GB
openchat_3.5-gpt-4-80k.Q4_0.ggufQ4_03.83GB
openchat_3.5-gpt-4-80k.IQ4_NL.ggufIQ4_NL3.87GB
openchat_3.5-gpt-4-80k.Q4_K_S.ggufQ4KS3.86GB
openchat_3.5-gpt-4-80k.Q4_K.ggufQ4_K4.07GB
openchat_3.5-gpt-4-80k.Q4_K_M.ggufQ4KM4.07GB
openchat_3.5-gpt-4-80k.Q4_1.ggufQ4_14.24GB
openchat_3.5-gpt-4-80k.Q5_0.ggufQ5_04.65GB
openchat_3.5-gpt-4-80k.Q5_K_S.ggufQ5KS4.65GB
openchat_3.5-gpt-4-80k.Q5_K.ggufQ5_K4.78GB
openchat_3.5-gpt-4-80k.Q5_K_M.ggufQ5KM4.78GB
openchat_3.5-gpt-4-80k.Q5_1.ggufQ5_15.07GB
openchat_3.5-gpt-4-80k.Q6_K.ggufQ6_K5.53GB
openchat_3.5-gpt-4-80k.Q8_0.ggufQ8_07.17GB

Original model description: --- license: apache-2.0 ---

Description

This model is finetuned on the distillation data from GPT-4. The base model is openchat/openchat_3.5

Usage

The model has a query format as in openchat_3.5.

GPT4 Correct User: {query}<|end_of_turn|>GPT4 Correct Assistant: {answer}<|end_of_turn|>