You can deploy this model and start earning money today!

AronDaron/
Qwen2.5-Coder-7B-Instruct-DatasetGen-v2

Name: Qwen2.5-Coder-7B-Instruct-DatasetGen-v2
Availability: InStock

Views

No views yet

Qwen2.5-Coder-7B-Instruct — Dataset Generator V2 Fine-tune

Fine-tuned version of Qwen2.5-Coder-7B-Instruct trained on Dataset Generator V2 — synthetic coding dataset generated with Dataset Generator.

Model	HumanEval	HumanEval+
Base Qwen2.5-Coder-7B-Instruct	55.5% (±2.1)	49.0% (±1.9)
This model (FT V2)	60.0% (±0.9)	54.0% (±1.8)

+4.5pp on HumanEval, +5.0pp on HumanEval+ vs base — error bars don't overlap, statistically significant improvement (5 runs averaged).

Training logs and exact hyperparameters were not preserved — this was an exploratory fine-tune.

Trained on Dataset Generator V2 — 1,135 multi-turn conversations across 8 coding categories:

See the dataset card for full details including generation models and methodology.

Optimized for algorithmic coding and reasoning — shows measurable improvement on HumanEval/HumanEval+
Not optimized for library-heavy workflows (pandas, numpy, requests) — for those use cases, train on a dataset with library-focused categories using Dataset Generator
Multi-turn conversational style — produces explanations alongside code

If this helped you:

Apache-2.0 — inherited from base model Qwen2.5-Coder-7B-Instruct.