MDL
Qwen2.5-Coder-7B-Instruct
Qwen
Parameters
7B
Downloads
1.9M
on HF
Likes
751
Avg score
28.1
6 benchmarks
Weights
Open
Released
Sep 17, 2024
About
Qwen2.5-Coder-7B-Instruct is a 7B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 28.1.
apache-2.0text-generation
Benchmark scores · 6
avg 28.1 — higher is betterThe research behind this model
all papers mentioning it →Qwen2.5-Coder Technical ReportYaRN: Efficient Context Window Extension of Large Language ModelsQwen2 Technical ReportSemantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent ResponsesMay 27, 2026Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement LearningMay 18, 2026When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository ContextMay 14, 2026Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA GenerationMay 13, 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.