Model hub and library. ThoughtWorks Radar: Adopt. 135K GitHub stars, 12M weekly downloads.
Metrics
GitHub Stars
135K
GitHub repository popularity
Radar Status
adopt
ThoughtWorks Technology Radar assessment
Framework Type
model_hub
Primary framework purpose
Weekly Downloads
12.0M
Package manager install frequency
Score Breakdown
adoption
30%96
Community size, growth velocity, and industry usage
ecosystem
25%92
Integrations, plugins, and extension availability
performance
30%88
Execution speed, latency, and resource efficiency
Compatibility(3)
Sources(1)
Related Signals(2)
gte-Qwen2-7B-instruct Leads MTEB Embedding Leaderboard
ModelsDec 28
92Alibaba's gte-Qwen2-7B-instruct has claimed the top position on MTEB with ~70% overall score, excelling in retrieval (nDCG@10) and semantic textual similarity tasks. The 7B parameter model with 3584 dimensions outperforms NVIDIA's NV-Embed-v2 and Voyage AI's voyage-3-large.
Related:
Embedding Models Establish New Category in AI Stack
ModelsDec 28
86Text embedding models have emerged as a distinct category in the AI stack, with MTEB standardizing evaluation across 8 task types. The top performers (gte-Qwen2, NV-Embed-v2, voyage-3-large) achieve ~70% overall scores with vector dimensions ranging from 768 to 4096, enabling specialized retrieval and semantic search applications.
Related: