Pre-selection of models to consider across languages for Alpha - Only the Cohere models are currently served by Inference Providers
Yacine Jernite
P(doom) Rejects the premise
AI & ML interests
Technical, community, and regulatory tools of AI governance @HuggingFace
Recent Activity
updated a model about 20 hours ago
yjernite/ncii-edit-guard-270m-v1 updated a dataset about 20 hours ago
yjernite/ncii-guard-eval-v1 updated a model about 20 hours ago
yjernite/ncii-edit-guard-270m-v2Organizations
Text embedding models I use
-
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 3.6M • • 2.01k -
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 8.75M • • 1.27k -
Qwen/Qwen3-Embedding-4B-GGUF
4B • Updated • 42.6k • 134 -
ibm-granite/granite-embedding-english-r2
Feature Extraction • 0.1B • Updated • 53.9k • 91
Models for local deployment
Document processing
Cybersecurity
super-smol to fine-tune
Inference-supported production models
List of recent models to use through HF inference providers
-
CohereLabs/command-a-vision-07-2025
Image-Text-to-Text • 112B • Updated • 18.6k • • 88 -
Qwen/Qwen3-235B-A22B-Instruct-2507
Text Generation • 235B • Updated • 166k • • 806 -
Qwen/Qwen3-32B
Text Generation • 33B • Updated • 3.47M • • 754 -
openai/gpt-oss-120b
Text Generation • 117B • Updated • 3.85M • • 5.38k
Privacy
Model picker - potluck
Pre-selection of models to consider across languages for Alpha - Only the Cohere models are currently served by Inference Providers
Cybersecurity
Text embedding models I use
-
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 3.6M • • 2.01k -
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 8.75M • • 1.27k -
Qwen/Qwen3-Embedding-4B-GGUF
4B • Updated • 42.6k • 134 -
ibm-granite/granite-embedding-english-r2
Feature Extraction • 0.1B • Updated • 53.9k • 91
super-smol to fine-tune
Models for local deployment
Inference-supported production models
List of recent models to use through HF inference providers
-
CohereLabs/command-a-vision-07-2025
Image-Text-to-Text • 112B • Updated • 18.6k • • 88 -
Qwen/Qwen3-235B-A22B-Instruct-2507
Text Generation • 235B • Updated • 166k • • 806 -
Qwen/Qwen3-32B
Text Generation • 33B • Updated • 3.47M • • 754 -
openai/gpt-oss-120b
Text Generation • 117B • Updated • 3.85M • • 5.38k
Document processing
Privacy