Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
2.6
TFLOPS
1
John
IlikeLLM
Follow
0 followers
·
1 following
AI & ML interests
llm
Recent Activity
new
activity
about 1 month ago
unsloth/Qwen3-VL-8B-Thinking-FP8:
Why is the pad token of all QWEN VL models in Unsloth "<|vision_pad|>", while QWEN officially uses "pad_token": "<|endoftext|>"
new
activity
about 1 month ago
unsloth/Qwen3-VL-8B-Thinking-FP8:
Why is the pad token of all QWEN VL models in Unsloth "<|vision_pad|>", while QWEN officially uses "pad_token": "<|endoftext|>"
updated
a collection
about 1 year ago
moe
View all activity
Organizations
None yet
Collections
1
moe
microsoft/Phi-3.5-MoE-instruct
Text Generation
•
42B
•
Updated
Mar 7
•
107k
•
564
moe
microsoft/Phi-3.5-MoE-instruct
Text Generation
•
42B
•
Updated
Mar 7
•
107k
•
564
models
0
None public yet
datasets
0
None public yet