Sinan Akkoyun
SinanAkkoyun
AI & ML interests
VLM / LLM, any to latent space encoding
Organizations
SinanAkkoyun's activity
Will there be training based on qwen2.5 later
5
#12 opened 7 months ago
by
michaelj
Molmo-7B-D-0924 OOM on A100 80GB using Quick Start code
1
5
#1 opened 7 months ago
by
sasawq21
batch inference supported?
1
7
#7 opened 7 months ago
by
chenkq
Done
#10 opened 7 months ago
by
SinanAkkoyun

Qwen Separation, understanding modeling
1
#5 opened 7 months ago
by
SinanAkkoyun

VRAM - how to run
2
#6 opened 7 months ago
by
SinanAkkoyun

Model is not inferencing on multiple images; is this the right template?
4
#4 opened about 1 year ago
by
ltbd78
Please publish LLM 1.7b base
2
#2 opened about 1 year ago
by
SinanAkkoyun

llm-1.3b-base
1
#2 opened about 1 year ago
by
SinanAkkoyun

One or two models during inference?
3
#3 opened over 1 year ago
by
Venkman42

updating n_kv_heads in config.json
2
#2 opened over 1 year ago
by
fwtan
Unofficial dataset
10
9
#2 opened over 1 year ago
by
SinanAkkoyun

Dataset
33
#1 opened almost 2 years ago
by
mdegans
Why not the new prompt format?
2
#1 opened almost 2 years ago
by
SinanAkkoyun

❤️❤️❤️❤️
1
#1 opened almost 2 years ago
by
SinanAkkoyun

TGI unwanted chinese output
1
#2 opened almost 2 years ago
by
SinanAkkoyun

H100 TransformerEngine
3
#14 opened almost 2 years ago
by
SinanAkkoyun

Question about VRAM requirements
4
#12 opened almost 2 years ago
by
sebastiaanvandenbroeck