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

(Trained with Unsloth)

(Trained with Unsloth)

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

(Trained with Unsloth)

(Trained with Unsloth)

Update README.md

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

Create config.json

Delete config.json

Update README.md

(Trained with Unsloth)

(Trained with Unsloth)

Upload README.md with huggingface_hub

initial commit