Not Me
overhead520
AI & ML interests
None yet
Recent Activity
updated a Space 1 day ago
overhead520/Unhinged-ERP-Benchmark updated a Space 1 day ago
overhead520/LLM-Settings-Guide new activity 13 days ago
antirez/glm-5.3-gguf:Inference speeds compared to DS4.1 Flash?Organizations
Inference speeds compared to DS4.1 Flash?
1
#2 opened 30 days ago
by
x-polyglot-x
Which Qwen3.8-27b-Uncensored model was used?
1
#14 opened about 1 month ago
by
SteveHere
Upstream tensor naming
➕ 2
3
#24 opened 27 days ago
by
2002c07525c77c06
Jailbreak doesn't seem to work for reasoning model with multiple characters.
1
#5 opened 3 months ago
by
AphidHf
request aifeifei798 / gemma-4-12B-Queen-it-qat-q4_0-unquantized
2
#9 opened 3 months ago
by
nyueki
Kimi K3?
2
#7 opened 3 months ago
by
notzgok
About your comment for Mistral V7 templates
❤️ 1
2
#2 opened 6 months ago
by
Dobratr
Gemma 4 Jailbreak prompt no worky
1
#4 opened 5 months ago
by
calif94577
Thoughts on grok 4.1/4.2
1
#8 opened 3 months ago
by
Toothless12345
request Gemma-4-Queen-31B-it
❤️ 1
6
#3 opened 6 months ago
by
EloyOn
These categories are not self explanatory.
1
#5 opened 4 months ago
by
NeonScreams
How are you using Qwen3-VL-235b-a22b-Thinking
1
#4 opened 5 months ago
by
steranium
fix a typo :)
1
#3 opened 5 months ago
by deleted
Idea: Try base models with jailbreaks (they can beat Heretics!)
❤️ 4
3
#662 opened 6 months ago
by
Iwaku-Real
Thank you.
1
#1 opened 6 months ago
by
Zouna
Guilherme34/Firefly-V3
👍 1
3
#2 opened 6 months ago
by
Guilherme34
Where's Impish?
🤗 1
2
#1 opened 8 months ago
by
SicariusSicariiStuff
Awful loss of coherence between MLX 2bit and IQ2_XSS 🙀
7
#2 opened about 1 year ago
by
overhead520
Awful loss of coherence between MLX 2bit and IQ2_XSS 🙀
7
#2 opened about 1 year ago
by
overhead520
Awful loss of coherence between MLX 2bit and IQ2_XSS 🙀
7
#2 opened about 1 year ago
by
overhead520