The model is converted from the original Qwen/Qwen2.5-Coder-3B-Instruct using:
litert-torch export_hf \
--model=Qwen/Qwen2.5-Coder-3B-Instruct \
--output_dir="./dynamic_wi8_afp32" \
--quantization_recipe="dynamic_wi8_afp32" \
--bundle_litert_lm=true
- Downloads last month
- 175
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support