Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 7.15M • • 16k
NIkita Balakin
Kotokin
AI & ML interests
None yet
Recent Activity
new activity about 1 month ago
lued/Qwen3.8-27B-INT8-W8A16-MTP:Quantization liked a model about 1 month ago
Qwen/Qwen3.8-27B updated a model 3 months ago
Kotokin/MMv1-ggufOrganizations
None yet
Quantization
👍 1
1
#6 opened about 1 month ago
by Kotokin
liked a
model about 1 month ago
updated a
model 3 months ago
published a
model 3 months ago
updated a
model 3 months ago
published a
model 3 months ago
Evaluation request
#443 opened 10 months ago
by Kotokin
The older version, please.
#1 opened 10 months ago
by Kotokin
liked a
model over 1 year ago
reacted to csabakecskemeti's post with 👍 over 1 year ago
Post
2008
-UPDATED-
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.
- 4 replies
replied to csabakecskemeti's post over 1 year ago
How many tokens per second do you receive? I didn't see this on the blog.
liked a
model over 1 year ago
updated a
model almost 2 years ago
The question of training the model.
1
#2 opened almost 2 years ago
by Kotokin
liked a
model almost 2 years ago
Where config.json?
10
#1 opened almost 2 years ago
by 
TheDrummer
liked a
model almost 2 years ago
reacted to BlinkDL's post with 👀 almost 2 years ago
Post
5893
RWKV-7 "Goose" preview rc2 => Peak RNN architecture?😃Will try to squeeze more performance for the final release. Preview code & model: https://github.com/BlinkDL/RWKV-LM/tree/main/RWKV-v7
- 2 replies
updated a
model about 2 years ago
liked a
model about 2 years ago
