Uploaded finetuned model

  • Developed by: didula-wso2
  • License: apache-2.0
  • Finetuned from model : didula-wso2/Qwen3-8B_julia_alpaca_ep4sft_16bit_vllm

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
534
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for didula-wso2/Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm

Finetuned
(14)
this model
Finetunes
1 model