Steve Li
CHNtentes
AI & ML interests
None yet
Recent Activity
new activity
5 days ago
bartowski/THUDM_GLM-4-32B-0414-GGUF:Broken results
liked
a model
5 days ago
THUDM/GLM-4-32B-0414
new activity
11 days ago
moonshotai/Kimi-VL-A3B-Thinking:gguf?
Organizations
None yet
CHNtentes's activity
Broken results
1
8
#2 opened 12 days ago
by
RamoreRemora
gguf?
13
7
#1 opened 17 days ago
by
AlgorithmicKing

Can we use existed llama 3.1 gguf
6
#1 opened 11 days ago
by
CHNtentes
Unethical comparisons with Deepseek replacing chinese languages by thai/vietnamese only
9
5
#32 opened 21 days ago
by
krustik
SigLIP or SigLIP2 encoder?
7
#48 opened 25 days ago
by
orrzohar

Downloading weights without duplicates
2
#52 opened 26 days ago
by
vadimkantorov
听我说谢谢你因为有你温暖了四季
3
4
#37 opened about 1 month ago
by
iwangdy
Can this be quantized with bitsAndBytes?
8
#6 opened about 1 month ago
by
Permahuman
Int4为什么比没量化的float32和float16还慢
1
#3 opened about 2 months ago
by
hujianmin
Maybe rename it 15B
2
#5 opened about 2 months ago
by
CHNtentes
Quantized models with vision included?
12
#27 opened about 1 month ago
by
geoad
When will you fix the model replies missing</think>\n start tags
17
#19 opened about 2 months ago
by
xldistance
When running example got ValueError: Attention mask should be of size (1, 1, 1, 30), but is torch.Size([1, 1, 1, 29])
6
#9 opened about 2 months ago
by
Phando

Why change the configuration of the tokenizer?
2
2
#4 opened 3 months ago
by
Lingrui

Quality vs 4bnb version
5
#2 opened 3 months ago
by
supercharge19
System Prompt
8
#2 opened 3 months ago
by
Wanfq

Thieves!
9
#36 opened 3 months ago
by
supercharge19
这我也跑不动啊你们都是在拿什么玩意玩啊。我勒个公鸡母鸡战斗鸡啊
5
#8 opened 4 months ago
by
ss996