Nathan
DreamFast
AI & ML interests
Local LLM
Recent Activity
new activity 3 days ago
zai-org/GLM-5.2:Please FUCK Anthropic updated a model 16 days ago
DreamFast/Qwen3-VL-8B-Heretic-1.3.0 published a model 16 days ago
DreamFast/Qwen3-VL-8B-Heretic-1.3.0Organizations
Please FUCK Anthropic
❤️🚀 97
16
#6 opened 4 days ago
by
6cf
Benchmarking and KL Divergence Difference
7
#1 opened 21 days ago
by
DreamFast
Independent verification: lowest KL of all 13 variants, capability fully preserved
🚀🔥 3
4
#1 opened 21 days ago
by
DreamFast
Independent verification: 99.5% ASR with capability preserved
👍 1
1
#2 opened 21 days ago
by
DreamFast
Independent benchmark verification: your Gemma 4 variant is the top pick
❤️ 1
#2 opened 21 days ago
by
DreamFast
Independent verification of refusal rate and language modelling quality
🔥 1
1
#2 opened 21 days ago
by
DreamFast
Analysis of wangzhang/gemma-4-E2B-it-abliterated compared to others
#2 opened 21 days ago
by
DreamFast
Independent verification of KL divergence and capability impact
#1 opened 21 days ago
by
DreamFast
New activity in DreamFast/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 24 days ago
Basically base on that analysis, Huihui is better than ton of finetunes in throughput
1
#4 opened 24 days ago
by
Jahaz
New activity in DreamFast/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 27 days ago
NVFP4 version?
3
#3 opened about 1 month ago
by
hdnh2006
Benchmarks and Chain of Thought
6
#8 opened about 1 month ago
by
DreamFast
Abliterix and other abliteration techniques
3
#1 opened about 1 month ago
by
DreamFast
New activity in DreamFast/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark about 1 month ago
Thank you
1
#1 opened about 1 month ago
by
MRU4913
Would you provide a safetensor version of models?
👍 6
2
#8 opened 3 months ago
by
beatlicpse
safetensor version
👀👍 8
1
#10 opened 2 months ago
by
Balfiky
"These are meant to be the best lossless uncensored models out there."
👀 18
1
#3 opened 2 months ago
by
daniel-dona
safetensor?
👀 3
10
#4 opened about 2 months ago
by
MRU4913
The model won't generate text if image input is enabled with TextGenerateLTX2Prompt
2
#1 opened about 2 months ago
by
squeeker
Eval request: HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
❤️ 3
5
#590 opened 3 months ago
by
mildsarcasm
why vision tower layers not included in comfyui version?
9
#5 opened 3 months ago
by
shivshankar