Qwen3.5-9B Phase 4 Specialization LoRA

Dataset: phase4_final_mix

Train file: /home/jica/repo/rocm_unsloth/qwen3_5_9B_finetuning/datasets/phase4_final_mix/train.jsonl

Train rows: 30966

This adapter continues jica98/qwen3.5-9b-phase3-reasoning-distill-lora on the documented Phase 4 final mix. It is produced by qwen3_5_9B_finetuning/train_phase4_specialize.py.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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

Model tree for jica98/qwen3.5-9b-phase4-specialize-lora

Base model

jica98/qwen3.5-9b-phase3-reasoning-distill-lora

Finetuned

(1)

this model