Qwen/Qwen2.5-7B-Instruct 路 finetune

Trained with Axeron ModelForge.

  • Method: finetune
  • Base model: Qwen/Qwen2.5-7B-Instruct
  • Training steps: 400
  • Final loss: 0.1747
Downloads last month
17
Safetensors
Model size
8B params
Tensor type
BF16
路
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for AxeronAI/axeron-mf-56

Base model

Qwen/Qwen2.5-7B
Finetuned
(3146)
this model