winninghealth/WiNGPT-Babel
Text Generation
•
Updated
•
245
•
33
Jack
qwertyjack
AI & ML interests
None yet
Recent Activity
new activity
about 2 months ago
Qwen/QwQ-32B:issue of "think too much" ，how to？(chinese)
new activity
3 months ago
unsloth/DeepSeek-R1-GGUF:Where did the BF16 come from?
Organizations
qwertyjack's activity
issue of "think too much" ，how to？(chinese)
2
#14 opened about 2 months ago
by
fenglui
Where did the BF16 come from?
8
#10 opened 3 months ago
by
gshpychka
New research paper, R1 type reasoning models can be drastically improved in quality
2
#19 opened 3 months ago
by
krustik
liked
a
model
3 months ago
Please make V3-lite
45
4
#12 opened 4 months ago
by
rombodawg
updated
a
model
5 months ago
感觉新版的Mistrial-LargeV3的GPTQ量化的int4版本对显存的需求大大提升了
2
#1 opened 5 months ago
by
YanchengQian
upvoted
an
article
7 months ago
Article
Making LLMs lighter with AutoGPTQ and transformers
•
50
upvoted
an
article
8 months ago
Article
TGI Multi-LoRA: Deploy Once, Serve 30 Models
•
57
How to run the model OpenGVLab/InternVL2-40B-AWQ with vllm docker image?
2
#2 opened 9 months ago
by
andryevinnik
updated
a
collection
10 months ago
liked
2
models
10 months ago
请教一下，cogvlm和glm4v的区别是什么呢
8
3
#1 opened 11 months ago
by
rangehow
Having trouble loading this with transformers
3
5
#8 opened about 1 year ago
by
codelion
GPTQ plz
10
#3 opened 12 months ago
by
Parkerlambert123
Would you plan to optimize ChatGLM2-6B? and when?
4
#47 opened over 1 year ago
by
Zuyuan
liked
a
Space
almost 2 years ago