👋 Open to Work

Sailor丶JS

sailorjs0804

·

sailorjs0804

AI & ML interests

SpeechLM & Harness

Recent Activity

new activity less than a minute ago

orcarouter/Qwen3.8-27B-Uncensored-NVFP4:ERROR: ValueError: There is no module or parameter named 'lm_head.weight_scale' in Qwen3_5ForCausalLM. The available parameters belonging to lm_head (ParallelLMHead) are: {'lm_head.weight'}

new activity about 9 hours ago

orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF:Q6_K looks reachable: the PLE tensor is 51.2B, not ~66B

new activity about 9 hours ago

orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF:i have a question

View all activity

Organizations

upvoted a collection 1 day ago

Qwen3.8 Flash Next Uncensored / Abliterated

5 items • Updated 2 days ago • 6

upvoted a collection 5 days ago

Qwen3.8 27B Uncensored / Abliterated

The Qwen3.8-27B-Uncensored family from OrcaRouter 🐋 FP8 ✅ NVFP4 ✅ GGUF ✅ INT8 ✅ MLX ✅ Full precision ✅ • 6 items • Updated 9 days ago • 65

upvoted a paper 5 days ago

Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors

Paper • 2608.22872 • Published 6 days ago • 7