Tinker LoRA Adapter
This repository contains a LoRA adapter exported from Tinker.
Usage
from transformers import AutoModelForCausalLM
adapter_id = "link-failed/SeeThat-PerfCodeBench-Qwen3.6-35B-A3B"
base_model = "Qwen/Qwen3.6-35B-A3B"
model = AutoModelForCausalLM.from_pretrained(adapter_id, device_map="auto")
Details
- Base model: Qwen/Qwen3.6-35B-A3B
- LoRA rank: 32
- Trained modules: attn=True, mlp=True, unembed=True
- Downloads last month
- 43
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for link-failed/SeeThat-PerfCodeBench-Qwen3.6-35B-A3B
Base model
Qwen/Qwen3.6-35B-A3B