gdscript-assistant / requirements.txt
vivekchakraverty's picture
Load Qwen2.5-Coder-7B in 4-bit (nf4) inside the GPU worker
2709f63
raw
history blame contribute delete
406 Bytes
gradio>=4.44
spaces>=0.30
torch
transformers~=4.45 # satisfies BOTH jina remote code (4.x) AND Qwen2.5-Coder
bitsandbytes>=0.43 # 4-bit (nf4) quantization of the 7B for ZeroGPU
sentence-transformers~=2.7
einops # required by jina remote code
accelerate # device_map model loading
faiss-cpu>=1.8
numpy
gdtoolkit>=4.0 # GDScript syntax parse + lint