Quantization made by Richard Erkhov.
Llama-3-Base-8B-SFT - GGUF
- Model creator: https://huggingface.co/princeton-nlp/
- Original model: https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT/
Name | Quant method | Size |
---|---|---|
Llama-3-Base-8B-SFT.Q2_K.gguf | Q2_K | 2.96GB |
Llama-3-Base-8B-SFT.IQ3_XS.gguf | IQ3_XS | 3.28GB |
Llama-3-Base-8B-SFT.IQ3_S.gguf | IQ3_S | 1.61GB |
Llama-3-Base-8B-SFT.Q3_K_S.gguf | Q3_K_S | 0.77GB |
Llama-3-Base-8B-SFT.IQ3_M.gguf | IQ3_M | 3.52GB |
Llama-3-Base-8B-SFT.Q3_K.gguf | Q3_K | 3.74GB |
Llama-3-Base-8B-SFT.Q3_K_M.gguf | Q3_K_M | 3.74GB |
Llama-3-Base-8B-SFT.Q3_K_L.gguf | Q3_K_L | 4.03GB |
Llama-3-Base-8B-SFT.IQ4_XS.gguf | IQ4_XS | 4.18GB |
Llama-3-Base-8B-SFT.Q4_0.gguf | Q4_0 | 4.34GB |
Llama-3-Base-8B-SFT.IQ4_NL.gguf | IQ4_NL | 4.38GB |
Llama-3-Base-8B-SFT.Q4_K_S.gguf | Q4_K_S | 4.37GB |
Llama-3-Base-8B-SFT.Q4_K.gguf | Q4_K | 4.58GB |
Llama-3-Base-8B-SFT.Q4_K_M.gguf | Q4_K_M | 4.58GB |
Llama-3-Base-8B-SFT.Q4_1.gguf | Q4_1 | 4.78GB |
Llama-3-Base-8B-SFT.Q5_0.gguf | Q5_0 | 5.21GB |
Llama-3-Base-8B-SFT.Q5_K_S.gguf | Q5_K_S | 5.21GB |
Llama-3-Base-8B-SFT.Q5_K.gguf | Q5_K | 5.34GB |
Llama-3-Base-8B-SFT.Q5_K_M.gguf | Q5_K_M | 5.34GB |
Llama-3-Base-8B-SFT.Q5_1.gguf | Q5_1 | 5.65GB |
Llama-3-Base-8B-SFT.Q6_K.gguf | Q6_K | 6.14GB |
Llama-3-Base-8B-SFT.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description: This is a model released from the preprint: SimPO: Simple Preference Optimization with a Reference-Free Reward Please refer to our repository for more details.