caio vicentino PRO
caiovicentino1
AI & ML interests
None yet
Recent Activity
updated a model 8 days ago
caiovicentino1/Qwen3.8-27B-GPTQ-gs64-FOEM published a model 8 days ago
caiovicentino1/Qwen3.8-27B-GPTQ-gs64-FOEM liked a model 23 days ago
deepseek-ai/DeepSeek-V4-Flash-0731Organizations
None yet
how did you create this before the paper was even released ?
1
#1 opened 4 months ago
by
saadadaw
caiovicentino1/MiniMax-M2.7-HLWQ-Q5
1
#1 opened 4 months ago
by
trentbarry
GPTQ + KV TQ4 local results: HumanEval ~ 67.68%
1
#2 opened 4 months ago
by
shawnqiu
Much better than v5
5
#1 opened 4 months ago
by
sverinn
ComfyUI Support
👍 1
4
#2 opened 4 months ago
by
FearL0rd
How can I enable vision ability
1
#1 opened 4 months ago
by
billbum
Will the rest of the generation modes be added?
1
#1 opened 4 months ago
by
doogyhatts
Broken MTP (speculative decoding)
7
#2 opened 5 months ago
by
Arien0
Humaneval: Base vs Polarquant vs FOEM
🔥 1
6
#3 opened 5 months ago
by
Arien0
what is polarquant and what diff is making compared to actual animate?
3
#1 opened 5 months ago
by
Perfs
Got model loading error
4
#2 opened 5 months ago
by
attashe
Please , can you make an polarQuant version of the abliterated one ?
4
#1 opened 5 months ago
by
Edward-Phantom
Serve with vLLM
1
#1 opened 5 months ago
by
meigami
Model not loading vLLM 0.19.0
7
#1 opened 5 months ago
by
Arien0
Do you convert it to BF16 to perform the inference?
11
#1 opened 5 months ago
by
Alissonerdx
Update chat_template.jinja
1
#1 opened 5 months ago
by
armand0e
Update tokenizer_config.json
1
#2 opened 5 months ago
by
armand0e
Is this AWQ type quant compatible with transformers/vLLM
2
#1 opened 5 months ago
by
jc2375