jina-reranker-v3.5
Collection
Domain-Ready Listwise Document Reranker • 4 items • Updated • 4
Felix
numb3r3
AI & ML interests
None yet
Recent Activity
updated a collection 4 days ago
jina-reranker-v3.5 updated a model 4 days ago
jinaai/jina-reranker-v3.5 published a model 4 days ago
jinaai/jina-reranker-v3.5-GGUFOrganizations
updated a
collection 4 days ago
updated a
model 4 days ago
published a
model 4 days ago
updated a
model 4 days ago
GGUF Please
5
#3 opened 6 days ago
by 
o0Linny0o
Any plans to merge text improvements into m0 / omni line?
2
#4 opened 6 days ago
by 
Brailagise
Demo for this model on Spaces
2
#2 opened 7 days ago
by 
multimodalart
published a
model 7 days ago
updated a
collection 7 days ago
updated a
model 10 days ago
published a
model 20 days ago
reacted to JonnaMat's post with 🚀 about 1 month ago
Post
1268
⚡ FlashHead: Fast LM Head Inference - Now a Simple vLLM Plugin
flash-head replaces the dense LM head with a two-stage retrieval pipeline - up to 2x inference speedup, training-free. Previously required custom Docker images; now it's just:
✨ The plugin activates automatically via vLLM's
🧩 Supported models (full collection):
Qwen Qwen3, 
meta-llama Llama3, 
google Gemma3, 
nvidia Cosmos-Reason2 - BF16 and W4A16 variants.
https://huggingface.co/collections/embedl/flashhead
📊 embedl/Edge-Inference-Benchmarks
🔧 Benchmark it yourself:
FlashHead shines at low batch sizes; the typical real-time / on-device use case. 🚀
flash-head replaces the dense LM head with a two-stage retrieval pipeline - up to 2x inference speedup, training-free. Previously required custom Docker images; now it's just:
pip install flash-head
vllm serve embedl/Qwen3-1.7B-FlashHead-W4A16✨ The plugin activates automatically via vLLM's
vllm.general_plugins entry point. No source patches, no custom imports.🧩 Supported models (full collection):
https://huggingface.co/collections/embedl/flashhead
📊 embedl/Edge-Inference-Benchmarks
🔧 Benchmark it yourself:
vllm bench latency --model embedl/Qwen3-1.7B-FlashHead-W4A16 --batch-size 1
# Baseline comparison
FLASHHEAD_ENABLED=0 vllm bench latency --model embedl/Qwen3-1.7B-FlashHead-W4A16 --batch-size 1FlashHead shines at low batch sizes; the typical real-time / on-device use case. 🚀
- 2 replies