Steve Li
CHNtentes
AI & ML interests
None yet
Recent Activity
new activity
about 12 hours ago
zai-org/GLM-4.6-FP8:Missing MTP?
upvoted
a
paper
1 day ago
Less is More: Recursive Reasoning with Tiny Networks
new activity
1 day ago
unsloth/GLM-4.5-Air-GGUF:What speed do you get at Q8 on AMD Ryzen™ AI Max+ 395
Organizations
None yet
Missing MTP?
4
#1 opened 8 days ago
by
jondurbin
What speed do you get at Q8 on AMD Ryzen™ AI Max+ 395
4
#14 opened 5 days ago
by
akierum
Quantization issues
4
#17 opened 15 days ago
by
stev236
Update README.md
1
#9 opened 18 days ago
by
CHNtentes
Error when using vLLM
➕
11
5
#2 opened 28 days ago
by
sheliak
Evaluation sloppiness / benchmark cheating?
👍
2
1
#9 opened 26 days ago
by
jaens
Corrected jinja template with tool Support works with PR llama.cpp/pull/15186
❤️
2
16
#9 opened 2 months ago
by
xbruce22
Error when running in VLLM
👍
2
18
#1 opened 29 days ago
by
d8rt8v
How much GPU memory is needed for local deployment?
13
#7 opened 30 days ago
by
XuehangCang
Plan for AWQ?
➕
24
2
#8 opened 30 days ago
by
hyunw55
Considering a distilled version of 80B parameters
➕
1
5
#2 opened about 1 month ago
by
snapo
changed tool call format?
1
#2 opened about 2 months ago
by
CHNtentes
Thanks!
❤️
2
5
#1 opened about 2 months ago
by
segmond
Context length: is it 128K (as mentioned in the model card) or 160K (as specified in config.json)?
1
#17 opened about 2 months ago
by
Lissanro
bro you forgot to put it under the v3.1 collection
👀
1
1
#12 opened about 2 months ago
by
DingzhenPearl
Why taking so long to add more information?
4
#12 opened about 2 months ago
by
cinnybun02
This just trades general performance for domain specific gains.
🔥
👍
15
11
#3 opened about 2 months ago
by
phil111
1.7b 2507?
👍
5
#7 opened about 2 months ago
by
CHNtentes
Gemma A3B
👍
5
13
#3 opened about 2 months ago
by
Maria99934
Text performance compared to GLM-4.5 Air
👀
5
2
#1 opened 2 months ago
by
Dampfinchen