RichardErkhov/OpenRLHF_-_Llama-3-8b-sft-mixture-gguf

Quantization made by Richard Erkhov.

Llama-3-8b-sft-mixture - GGUF

Model creator: https://huggingface.co/OpenRLHF/
Original model: https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture/

Name	Quant method	Size
Llama-3-8b-sft-mixture.Q2_K.gguf	Q2_K	2.96GB
Llama-3-8b-sft-mixture.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3-8b-sft-mixture.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3-8b-sft-mixture.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3-8b-sft-mixture.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3-8b-sft-mixture.Q3_K.gguf	Q3_K	3.74GB
Llama-3-8b-sft-mixture.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3-8b-sft-mixture.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3-8b-sft-mixture.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3-8b-sft-mixture.Q4_0.gguf	Q4_0	4.34GB
Llama-3-8b-sft-mixture.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3-8b-sft-mixture.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3-8b-sft-mixture.Q4_K.gguf	Q4_K	4.58GB
Llama-3-8b-sft-mixture.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3-8b-sft-mixture.Q4_1.gguf	Q4_1	4.78GB
Llama-3-8b-sft-mixture.Q5_0.gguf	Q5_0	5.21GB
Llama-3-8b-sft-mixture.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3-8b-sft-mixture.Q5_K.gguf	Q5_K	5.34GB
Llama-3-8b-sft-mixture.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3-8b-sft-mixture.Q5_1.gguf	Q5_1	5.65GB
Llama-3-8b-sft-mixture.Q6_K.gguf	Q6_K	6.14GB
Llama-3-8b-sft-mixture.Q8_0.gguf	Q8_0	7.95GB

Original model description:

library_name: transformers tags: []

Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT

We fixed the generation_config.json.

This is the SFT checkpoint used for the project Online-RLHF. Also, check the technical report here.

The model is trained from meta-llama/Meta-Llama-3-8B on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.

The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract.