CoolFace
Modelpublic

RichardErkhov/Fredithefish_-_RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes785downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4 - GGUF

  • —Model creator: https://huggingface.co/Fredithefish/
  • —Original model: https://huggingface.co/Fredithefish/RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4/
NameQuant methodSize
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q2_K.ggufQ2_K1.01GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.IQ3_XS.ggufIQ3_XS1.14GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.IQ3_S.ggufIQ3_S1.16GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q3_K_S.ggufQ3KS1.16GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.IQ3_M.ggufIQ3_M1.28GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q3_K.ggufQ3_K1.38GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q3_K_M.ggufQ3KM1.38GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q3_K_L.ggufQ3KL1.49GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.IQ4_XS.ggufIQ4_XS1.43GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q4_0.ggufQ4_01.49GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.IQ4_NL.ggufIQ4_NL1.5GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q4_K_S.ggufQ4KS1.5GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q4_K.ggufQ4_K1.66GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q4_K_M.ggufQ4KM1.66GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q4_1.ggufQ4_11.64GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q5_0.ggufQ5_01.8GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q5_K_S.ggufQ5KS1.8GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q5_K.ggufQ5_K1.93GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q5_K_M.ggufQ5KM1.93GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q5_1.ggufQ5_11.95GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q6_K.ggufQ6_K2.13GB
RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4.Q8_0.ggufQ8_02.75GB

Original model description: --- license: cc datasets:

  • —Fredithefish/Instruction-Tuning-with-GPT-4-RedPajama-Chat language:
  • —en inference: false --- <html> <head> <style> .alert { padding: 15px; background-color: #f44336; color: white; } </style> </head> <body> <div class="alert"> <strong>Warning:</strong> This fine-tuned model has only undergone 200 steps of fine-tuning and may not be reliable. The final model will not be released. </div> </body> </html> <br>

RedPajama-INCITE-Chat-3B-Instruction-Tuning-with-GPT-4

RedPajama-INCITE-Chat-3B Model finetuned <a href="https://huggingface.co/datasets/Fredithefish/Instruction-Tuning-with-GPT-4-RedPajama-Chat">on this dataset</a>

Reproduction

The code for the finetuning of this model can be found at https://github.com/fredi-python/Fine-tune-RedPajama-Chat-3B

Usage and License Notices

The Model is intended and licensed for research use only. The model is under the CC BY NC 4.0 license (allowing only non-commercial use)