miitarou
/

qwen25-7b-agentbench-sft05

Model card Files Files and versions

qwen25-7b-agentbench-sft05

Qwen2.5-7B-Instruct + LoRA SFT for AgentBench (DB Bench + ALFWorld)

Base model: Qwen/Qwen2.5-7B-Instruct
Training: LoRA SFT with assistant-only loss
Data: 72B distilled data + rule-based data

Downloads last month: 18

Safetensors

Model size

8B params

Tensor type

F16

·

Inference Providers NEW

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

Model tree for miitarou/qwen25-7b-agentbench-sft05

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2687)

this model