Rakushaking
/

Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo-d2

structured-data

Model card Files Files and versions

Final DPO: TOML + YAML + XML + codeblock fix

TOML: 750 pairs (section vs inline)
YAML: 300 pairs (correct vs broken indent)
XML: 300 pairs (valid vs broken tags)
JSON: 225 pairs (clean vs codeblock-wrapped)
CSV: 150 pairs
LR=1e-05, Beta=0.1, Epochs=1

Downloads last month: 2

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Rakushaking/Qwen4b-SFT-d9-merged-after-dpo-toml-xml-yaml-dpo-d2

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

Rakushaking/Qwen4b-SFT-d9

Finetuned

Rakushaking/Qwen4b-SFT-d9-merged-after-dpo-d2

Finetuned

(3)

this model