🔄 In a Training Loop

Hasan B.

hasanbasbunar

·

hasanbasbunar

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

RadixArk/Qwen3.8-Flash-Next-NVFP4:One-command deployment on a single DGX Spark (34-42 tok/s, prefix caching, 262K)

liked a model 9 days ago

RadixArk/Qwen3.8-27B-NVFP4-BF16-LMHead

updated a model 14 days ago

hasanbasbunar/Qwen3.8-27B-DSpark-Multilingual

View all activity

Organizations

New activity in RadixArk/Qwen3.8-Flash-Next-NVFP4 5 days ago

One-command deployment on a single DGX Spark (34-42 tok/s, prefix caching, 262K)

#7 opened 5 days ago by

New activity in empero-ai/Qwen3.8-27B-Ridge-GGUF 15 days ago

One-command deploy of this model on 16 GB GPUs (145k context, systemd, pinned)

#6 opened 15 days ago by

New activity in ornith-ai/Ornith-1.0-35B 2 months ago

Fix chat_template.jinja: drop hard raise_exception on message order (breaks tool-calling in llama.cpp/LM Studio/Ollama)

#10 opened 2 months ago by

New activity in coqui/xtts 8 months ago

Fix PyTorch 2.6+ weights_only=True unpickling error for XttsConfig

#100 opened 8 months ago by

New activity in agents-course/First_agent_template over 1 year ago

Update app.py

#152 opened over 1 year ago by