Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
WIlfLin
/
JEV-Qwen3.8-Flash-Next-Linear-Runtime
Like
0
Visual Question Answering
custom-code
decision-model
nvfp4
bf16
vllm
multimodal
image-text-to-text
License:
qwen-community-1.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
JEV-Qwen3.8-Flash-Next-Linear-Runtime
3.67 MB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
WIlfLin
Publish default Linear vLLM multimodal API and verified 86-label image runtime
1847787
verified
15 days ago
evaluations
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
head
Publish original BF16 linear head runtime and reproducible public evaluation (part 2)
16 days ago
jev
Publish original BF16 linear head runtime and reproducible public evaluation (part 2)
16 days ago
linear
Publish original BF16 linear head runtime and reproducible public evaluation (part 2)
16 days ago
multimodal
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
shared_head
Add opt-in shared-material reranking with measured multi-question cache reuse
15 days ago
shared_material
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
.gitattributes
Safe
1.52 kB
initial commit
16 days ago
LICENSE
Safe
3.24 kB
Publish original BF16 linear head runtime and reproducible public evaluation
16 days ago
README.md
4.62 kB
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
REPRODUCE.md
1.98 kB
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
SHA256SUMS.json
93.8 kB
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
download_weights.py
Safe
246 Bytes
Publish original BF16 linear head runtime and reproducible public evaluation
16 days ago
extract_choice_head.py
Safe
3.31 kB
Publish original BF16 linear head runtime and reproducible public evaluation (part 2)
16 days ago
run_benchmark.py
Safe
6.03 kB
Publish original BF16 linear head runtime and reproducible public evaluation (part 2)
16 days ago
serve_backend.sh
1.31 kB
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
serve_choice.py
Safe
2.88 kB
Reuse backend HTTP connections in verified BF16 linear runtime
15 days ago
serve_multimodal.py
192 Bytes
Publish default Linear vLLM multimodal API and verified 86-label image runtime
15 days ago
serve_shared_backend.sh
1.26 kB
Add opt-in shared-material reranking with measured multi-question cache reuse
15 days ago
