Gabriel Vamanu
gabbo1995
·
AI & ML interests
I love classification tasks, it's mesmerizing to comprehend how we take a decision and how we can explain a neural network to take decisions itself.
Recent Activity
liked a model 2 days ago
v-gen-ai/flux-calibri-gates new activity 26 days ago
unsloth/Qwen3.5-35B-A3B-GGUF:Vllm support new activity about 1 month ago
HuggingFaceM4/faster-qwen3-tts-demo:error: Offset increment outside graph capture :(Organizations
None yet
Vllm support
8
#15 opened 30 days ago
by 
deece
error: Offset increment outside graph capture :(
7
#1 opened about 1 month ago
by gabbo1995
Could you please provide an example of how this could be run in diffusers? Thank you!
👍 9
7
#1 opened 2 months ago
by gabbo1995
Diffusers nunchaku example code?
2
#5 opened 2 months ago
by gabbo1995
How to run from python script?
4
#3 opened 2 months ago
by 
fuadsm
is there a bug?
1
#1 opened 2 months ago
by gabbo1995
Does it use int8 kernel? Is it a way?
#1 opened 3 months ago
by gabbo1995
Could you please also provide a lightning merged version? Or can it use lightning loras?
#2 opened 3 months ago
by gabbo1995
can you please provide an example?
👍 1
8
#1 opened 3 months ago
by gabbo1995
Hi! can this be used with nunchaku?
➕ 2
#1 opened 3 months ago
by gabbo1995
Diffusers run gguf?
6
#2 opened 3 months ago
by gabbo1995
Guide to load this model
2
#3 opened 4 months ago
by 
tuandao-zenai
Thank you!
5
#1 opened 4 months ago
by gabbo1995
Can you please show an example.py to run this model?
2
#4 opened 4 months ago
by gabbo1995
Can this be used in diffusers with GGUF Configuration?
#1 opened 4 months ago
by gabbo1995
how to quantize my safetensors?
2
#1 opened 5 months ago
by gabbo1995
RedHatAI/gemma-3n-E4B-it-quantized.w4a16 is not a multimodal model
👍 1
2
#1 opened 8 months ago
by gabbo1995
Could you please tell me how to quantize my own finetune?
👍 1
1
#1 opened 5 months ago
by gabbo1995