MDL
Qwen2.5-7B-Instruct
Qwen
Parameters
7B
Downloads
12.6M
on HF
Likes
1.4K
Avg score
56.8
10 benchmarks
Weights
Open
Released
Sep 16, 2024
About
Qwen2.5-7B-Instruct is a 7B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 10 evals, averaging 56.8.
apache-2.0text-generation
Benchmark scores · 10
avg 56.8 — higher is betterThe research behind this model
all papers mentioning it →YaRN: Efficient Context Window Extension of Large Language ModelsQwen2 Technical ReportCoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test▲ 9 on HF · May 22, 2026Multimodal Music Recommendation System using LLMs▲ 1 on HF · May 28, 2026Qwen2.5-1M Technical Report8 cites · Jan 26, 2025On-Policy Replay for Continual Supervised Fine-TuningMay 28, 2026Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?May 26, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.