Quantization made by Richard Erkhov.
llama2-13b-dpo-v2 - GGUF
- Model creator: https://huggingface.co/mncai/
- Original model: https://huggingface.co/mncai/llama2-13b-dpo-v2/
Name | Quant method | Size |
---|---|---|
llama2-13b-dpo-v2.Q2_K.gguf | Q2_K | 4.52GB |
llama2-13b-dpo-v2.IQ3_XS.gguf | IQ3_XS | 4.99GB |
llama2-13b-dpo-v2.IQ3_S.gguf | IQ3_S | 5.27GB |
llama2-13b-dpo-v2.Q3_K_S.gguf | Q3_K_S | 5.27GB |
llama2-13b-dpo-v2.IQ3_M.gguf | IQ3_M | 5.57GB |
llama2-13b-dpo-v2.Q3_K.gguf | Q3_K | 5.9GB |
llama2-13b-dpo-v2.Q3_K_M.gguf | Q3_K_M | 5.9GB |
llama2-13b-dpo-v2.Q3_K_L.gguf | Q3_K_L | 6.45GB |
llama2-13b-dpo-v2.IQ4_XS.gguf | IQ4_XS | 6.54GB |
llama2-13b-dpo-v2.Q4_0.gguf | Q4_0 | 6.86GB |
llama2-13b-dpo-v2.IQ4_NL.gguf | IQ4_NL | 6.9GB |
llama2-13b-dpo-v2.Q4_K_S.gguf | Q4_K_S | 6.91GB |
llama2-13b-dpo-v2.Q4_K.gguf | Q4_K | 7.33GB |
llama2-13b-dpo-v2.Q4_K_M.gguf | Q4_K_M | 7.33GB |
llama2-13b-dpo-v2.Q4_1.gguf | Q4_1 | 7.61GB |
llama2-13b-dpo-v2.Q5_0.gguf | Q5_0 | 8.36GB |
llama2-13b-dpo-v2.Q5_K_S.gguf | Q5_K_S | 8.36GB |
llama2-13b-dpo-v2.Q5_K.gguf | Q5_K | 8.6GB |
llama2-13b-dpo-v2.Q5_K_M.gguf | Q5_K_M | 8.6GB |
llama2-13b-dpo-v2.Q5_1.gguf | Q5_1 | 9.1GB |
llama2-13b-dpo-v2.Q6_K.gguf | Q6_K | 9.95GB |
llama2-13b-dpo-v2.Q8_0.gguf | Q8_0 | 12.88GB |
Original model description: Entry not found