Tarek07/Legion-V2.1-LLaMa-70B
Text Generation
•
Updated
•
256
•
13
NIkita Balakin
Kotokin
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
Tarek07/Legion-V2.1-LLaMa-70B
reacted
to
csabakecskemeti's
post
with 👍
about 2 months ago
-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.
replied to
csabakecskemeti's
post
about 2 months ago
-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.
Organizations
None yet
Kotokin's activity
liked
a
model
about 1 month ago
reacted to
csabakecskemeti's
post with 👍
about 2 months ago
Post
1967
-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
about 2 months ago
How many tokens per second do you receive? I didn't see this on the blog.
liked
a
model
4 months ago
updated
a
model
4 months ago
The question of training the model.
1
#2 opened 5 months ago
by
Kotokin
Request for a 3.5 bpw
#1 opened 5 months ago
by
Kotokin
liked
a
model
5 months ago
Where config.json?
10
#1 opened 5 months ago
by
TheDrummer
liked
a
model
6 months ago
reacted to
BlinkDL's
post with 👀
7 months ago
Post
5645
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
9 months ago
liked
a
model
9 months ago
updated
a
model
9 months ago
The question is about the next model.
2
#8 opened 10 months ago
by
Kotokin
liked
a
model
10 months ago
liked
a
model
11 months ago
upvoted
a
collection
11 months ago
liked
2
models
12 months ago
