Steve Li
CHNtentes
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
deepseek-ai/DeepSeek-V3-0324:听我说谢谢你因为有你温暖了四季
new activity
2 days ago
Qwen/Qwen2.5-Omni-7B:Qwen2.5-Omni-7B-AWQ?
new activity
2 days ago
Qwen/Qwen2.5-Omni-7B:Can this be quantized with bitsAndBytes?
Organizations
None yet
CHNtentes's activity
听我说谢谢你因为有你温暖了四季
3
#37 opened 3 days ago
by
iwangdy
Qwen2.5-Omni-7B-AWQ?
1
#7 opened 2 days ago
by
CHNtentes
Can this be quantized with bitsAndBytes?
7
#6 opened 3 days ago
by
Permahuman
Int4为什么比没量化的float32和float16还慢
1
#3 opened 21 days ago
by
hujianmin
Maybe rename it 15B
2
#5 opened 24 days ago
by
CHNtentes
Quantized models with vision included?
12
#27 opened 10 days ago
by
geoad
Does it support thinking on/off?
5
#2 opened 9 days ago
by
CHNtentes
When will you fix the model replies missing</think>\n start tags
17
#19 opened 23 days ago
by
xldistance
Benchmark results compared to orig fp8 / int4 quants etc?
4
#1 opened about 1 month ago
by
CHNtentes
Why change the configuration of the tokenizer?
2
#4 opened 2 months ago
by
Lingrui

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

Thieves!
9
#36 opened 3 months ago
by
supercharge19
why use q5 for key cache?
1
#7 opened 3 months ago
by
CHNtentes
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 3 months ago
by
ss996
Can we use "temporal tiling support" with these gguf models?
1
#10 opened 3 months ago
by
CHNtentes
minimum vram?
11
#9 opened 3 months ago
by
CHNtentes