Volko
Volko76
AI & ML interests
Quantization, Fine-tune, Agentic Frameworks
Recent Activity
updated
a model
2 days ago
Volko76/Lucie-7B-Instruct-unsloth-bnb-4bit
published
a model
2 days ago
Volko76/Lucie-7B-Instruct-unsloth-bnb-4bit
updated
a model
2 days ago
OpenLLM-France/Lucie-7B-Instruct-gguf
Organizations
Volko76's activity
Performances
2
#2 opened 2 months ago
by
pierrealex
Does not work. The model size is wrong too. 1.5B x 5.5BPW should be ~1.6GB
4
#1 opened 2 months ago
by
imoc
I will soon create a quantized version of Lucie for people who don't know how to do it
5
#1 opened 2 months ago
by
Volko76
Is it possible to use this dataset to create a french instruct finetuned version of Qwen ?
#1 opened 2 months ago
by
Volko76
Thanks so much for this new release !! OpenSourceForTheBetter
2
#1 opened 2 months ago
by
Volko76
Thanks a lot for this awesome model
#19 opened 2 months ago
by
Volko76