Qwen2.5-Coder-32B SERA Toolcalls LoRA
This repository contains a LoRA/QLoRA adapter checkpoint trained from endsky/sera-4.5-django-t2-recall05-toolcalls dataset with Axolotl from Qwen/Qwen2.5-Coder-32B-Instruct.
Training
- Base model:
Qwen/Qwen2.5-Coder-32B-Instruct - Adapter: QLoRA
- LoRA rank: 32
- LoRA alpha: 64
- Sequence length: 49152
- Optimizer: paged_adamw_8bit
- Framework: Axolotl
Usage
Load this adapter with PEFT on top of the base model.
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for GatlingPeaShooter/qwen25-coder-32b-sera-toolcalls
Base model
Qwen/Qwen2.5-32B Finetuned
Qwen/Qwen2.5-Coder-32B Finetuned
Qwen/Qwen2.5-Coder-32B-Instruct