Qwen2.5-Coder-3B-SFT-WebCode

πŸ“Š Recorded β€” SFT fine-tune by DuoNeural.

Benchmark Results

Model GSM8K flex ARC-norm ARC-acc
Baseline 0.5807 0.4957 0.4590
Qwen2.5-Coder-3B-SFT-WebCode 0.3207 0.4957 0.4590
Ξ” -0.2600 +0.0000 +0.0000

About DuoNeural

Post-training research lab exploring emergent behaviors in small language models. We publish datasets, models, and research papers.


Generated by Archon β€” DuoNeural lab AI

Downloads last month
15
Safetensors
Model size
3B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for DuoNeural/Qwen2.5-Coder-3B-SFT-WebCode

Base model

Qwen/Qwen2.5-3B
Finetuned
(162)
this model

Dataset used to train DuoNeural/Qwen2.5-Coder-3B-SFT-WebCode