Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
FastFlowLM
/
Qwen3-4B-Thinking-2507-NPU2
like
1
Text Generation
Transformers
qwen3
conversational
arxiv:
2505.09388
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
main
Qwen3-4B-Thinking-2507-NPU2
3.31 GB
1 contributor
History:
6 commits
FastFlowLM
Update Version
cf31b34
verified
about 2 months ago
.gitattributes
Safe
1.86 kB
Init upload
about 2 months ago
README.md
Safe
10.1 kB
Upload README.md
about 2 months ago
attn.xclbin
698 kB
xet
Init upload
about 2 months ago
config.json
Safe
851 Bytes
Update Version
about 2 months ago
dequant.xclbin
115 kB
xet
Init upload
about 2 months ago
layer.xclbin
302 kB
xet
Init upload
about 2 months ago
lm_head.xclbin
153 kB
xet
Init upload
about 2 months ago
mm.xclbin
348 kB
xet
Init upload
about 2 months ago
model.q4nx
3.29 GB
xet
Init upload
about 2 months ago
tokenizer.json
11.4 MB
xet
Init upload
about 2 months ago
tokenizer_config.json
Safe
9.67 kB
Fix: Think Marker Missing
about 2 months ago