Vinay Saini

gameonvinay

gameonvinay

AI & ML interests

None yet

Recent Activity

new activity about 9 hours ago

gittensor-model-hub/Qwen3.8-27B-DSpark-NVFP4:Please share script for running in vllm

reacted to DavidAU's post with 🔥 about 10 hours ago

Qwen3.8 - 27B - COLD FUSION Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output. Increase in general intelligence too (all 7 critical benches); bench marks posted. Trained using the COLD FUSION method (GAIN + UNSLOTH). NOTE: This is NOT a heretic / uncensored version. MTP and GGUF NEO MAX quants: https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF SOURCE: https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

repliedto DavidAU's post about 10 hours ago

Qwen3.8 - 27B - COLD FUSION Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output. Increase in general intelligence too (all 7 critical benches); bench marks posted. Trained using the COLD FUSION method (GAIN + UNSLOTH). NOTE: This is NOT a heretic / uncensored version. MTP and GGUF NEO MAX quants: https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF SOURCE: https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

View all activity

Organizations

None yet

New activity in gittensor-model-hub/Qwen3.8-27B-DSpark-NVFP4 about 9 hours ago

Please share script for running in vllm

#2 opened about 9 hours ago by

New activity in unsloth/Qwen3.8-27B-NVFP4 5 days ago

Inferact/Qwen3.8-27B-NVFP4 is on vLLM's official documentation

#8 opened 5 days ago by

pathosethoslogos

New activity in sakamakismile/Qwen3.8-27B-MTP-NVFP4 5 days ago

Running in vllm getting this warning but not getting the same warning when running unsloth's NVFP4 version which is slightly bigger.

#1 opened 5 days ago by

New activity in kkuspa/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-NVFP4A16 19 days ago

FP8 KV cache calibration

#1 opened 20 days ago by

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP 21 days ago

Issues with Using Models in OpenCode

#4 opened 21 days ago by

New activity in PassingByPixels/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-NVFP4 23 days ago

MTP?

#1 opened 24 days ago by

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 23 days ago

NVFP4?

#2 opened about 1 month ago by

Loved this. Hope to get compatible weights for vllm

#26 opened 26 days ago by

New activity in palmfuture/Ornith-1.0-35B-NVFP4A16 about 2 months ago

Nice and Stable

#1 opened about 2 months ago by