10 days ago
-
Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head (#1)
- Re-convert with the Qwen MTP head (header.speculator): basertd --speculate mtp-head (c1229f9ca57caed08b9126c3983283eb436eb0a2)
-
Upload Qwen3.6-27B-cuda-q8.base with huggingface_hub
-
Upload Qwen3.6-27B-cuda-q4mix.base with huggingface_hub
-
Upload Qwen3.6-27B-Q8.base with huggingface_hub
-
Q4 bundle
-
model card + config
-
initial commit
