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

q6_k: Uses Q6_K for all tensors

q5_k_s: Uses Q5_K for all tensors

q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K

q5_0: Higher accuracy, higher resource usage and slower inference.

q4_k_s: Uses Q4_K for all tensors

q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K

q4_0: Original quant method, 4-bit.

q3_k_s: Uses Q3_K for all tensors

q3_k_m: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K

q3_k_l: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K

q2_k: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.

Create config.json

Delete config.json

q3_k_xs" : "3-bit extra small quantization

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q4_0.gguf to YugoGPT-Quantized-GGUF.Q4_0.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q6_K.gguf to YugoGPT-Quantized-GGUF.Q6_K.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q5_K_S.gguf to YugoGPT-Quantized-GGUF.Q5_K_S.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q5_0.gguf to YugoGPT-Quantized-GGUF.Q5_0.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q4_K_S.gguf to YugoGPT-Quantized-GGUF.Q4_K_S.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q3_K_L.gguf to YugoGPT-Quantized-GGUF.Q3_K_L.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q2_K.gguf to YugoGPT-Quantized-GGUF.Q2_K.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q3_K_S.gguf to YugoGPT-Quantized-GGUF.Q3_K_S.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantize-GGUF.Q4_K_M.gguf to YugoGPT-Quantized-GGUF.Q4_K_M.gguf

Rename YugoGPT-Quantized-GGUF-unsloth.Q5_K_M.gguf to YugoGPT-Quantized-GGUF.Q5_K_M.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Rename YugoGPT-Quantized-GGUF-unsloth.Q3_K_M.gguf to YugoGPT-Quantized-GGUF.Q3_K_M.gguf

(Trained with Unsloth)

(Trained with Unsloth)

Upload YugoGPT-Quantize-GGUF.Q4_K_M.gguf

Update README.md