Russell Dempsey

SgtPooki

AI & ML interests

None yet

Recent Activity

new activity 11 days ago

deepreinforce-ai/Ornith-1.0-35B:When will Ornit-2.0 will release based on Qwen-3.6-35b-a3b

new activity 12 days ago

deepreinforce-ai/Ornith-1.0-35B:NVFP4 quantization of Ornith-1.0-35B (single-Blackwell-GPU, vLLM-validated)

reacted to mlabonne's post with 🔥 15 days ago

✂️ AutoAbliteration I made a Colab notebook to automatically abliterate models. It's quite general, so you can do interesting stuff like blocking a given language in the model outputs. 💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing

View all activity

Organizations

None yet

New activity in deepreinforce-ai/Ornith-1.0-35B 11 days ago

When will Ornit-2.0 will release based on Qwen-3.6-35b-a3b

#27 opened 19 days ago by

New activity in deepreinforce-ai/Ornith-1.0-35B 12 days ago

NVFP4 quantization of Ornith-1.0-35B (single-Blackwell-GPU, vLLM-validated)

#20 opened about 1 month ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4 15 days ago

RTX 5090 numbers for the hardware compatibility matrix

#10 opened 15 days ago by

New activity in AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 3 months ago

Add a `quant_config` block (or rename the repo) so bf16 vs NVFP4 isn't ambiguous

#4 opened 3 months ago by