Ctrl+K

1 contributor

History: 60 commits

datatab

q8_0: Fast conversion. High resource use, but generally acceptable.

f161601 verified over 1 year ago

.gitattributes

4.28 kB

q8_0: Fast conversion. High resource use, but generally acceptable. over 1 year ago
README.md

3.42 kB

Update README.md over 1 year ago
YugoGPT-Quantized-GGUF.Q3_K_XS.gguf

3 GB
xet

q3_k_xs" : "3-bit extra small quantization over 1 year ago
YugoGPT-Quantized.GGUF.Q2_K.gguf

2.72 GB
xet

q2_k: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors. over 1 year ago
YugoGPT-Quantized.GGUF.Q3_K_L.gguf

3.82 GB
xet

q3_k_l: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K over 1 year ago
YugoGPT-Quantized.GGUF.Q3_K_M.gguf

3.52 GB
xet

q3_k_m: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K over 1 year ago
YugoGPT-Quantized.GGUF.Q3_K_S.gguf

3.16 GB
xet

q3_k_s: Uses Q3_K for all tensors over 1 year ago
YugoGPT-Quantized.GGUF.Q4_0.gguf

4.11 GB
xet

q4_0: Original quant method, 4-bit. over 1 year ago
YugoGPT-Quantized.GGUF.Q4_K_M.gguf

4.37 GB
xet

q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K over 1 year ago
YugoGPT-Quantized.GGUF.Q4_K_S.gguf

4.14 GB
xet

q4_k_s: Uses Q4_K for all tensors over 1 year ago
YugoGPT-Quantized.GGUF.Q5_0.gguf

5 GB
xet

q5_0: Higher accuracy, higher resource usage and slower inference. over 1 year ago
YugoGPT-Quantized.GGUF.Q5_K_M.gguf

5.13 GB
xet

q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K over 1 year ago
YugoGPT-Quantized.GGUF.Q5_K_S.gguf

5 GB
xet

q5_k_s: Uses Q5_K for all tensors over 1 year ago
YugoGPT-Quantized.GGUF.Q6_K.gguf

5.94 GB
xet

q6_k: Uses Q6_K for all tensors over 1 year ago
YugoGPT-Quantized.GGUF.Q8_0.gguf

7.7 GB
xet

q8_0: Fast conversion. High resource use, but generally acceptable. over 1 year ago
config.json

31 Bytes

Create config.json over 1 year ago