初始化项目，由ModelHub XC社区提供模型

Model: clowman/Llama-3.2-3B-Instruct-AWQ-Int4
Source: Original Platform

requirements-lambda-quant.txt

@@ -0,0 +1,83 @@
+accelerate==1.5.2
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiosignal==1.3.2
+annotated-types==0.7.0
+async-timeout==5.0.1
+attrs==25.3.0
+autoawq==0.2.8
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+compressed-tensors==0.9.2
+datasets==3.4.1
+device-smi==0.4.1
+dill==0.3.8
+einops==0.8.1
+filelock==3.18.0
+flash_attn==2.7.4.post1
+frozenlist==1.5.0
+fsspec==2024.12.0
+gekko==1.2.1
+gptqmodel==2.1.0
+hf_transfer==0.1.9
+huggingface-hub==0.29.3
+idna==3.10
+Jinja2==3.1.6
+llmcompressor==0.4.1
+logbar==0.0.3
+loguru==0.7.3
+MarkupSafe==3.0.2
+mpmath==1.3.0
+multidict==6.2.0
+multiprocess==0.70.16
+networkx==3.4.2
+numpy==1.26.4
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-cupti-cu12==12.4.127
+nvidia-cuda-nvrtc-cu12==12.4.127
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.2.1.3
+nvidia-curand-cu12==10.3.5.147
+nvidia-cusolver-cu12==11.6.1.9
+nvidia-cusparse-cu12==12.3.1.170
+nvidia-cusparselt-cu12==0.6.2
+nvidia-ml-py==12.570.86
+nvidia-nccl-cu12==2.21.5
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.4.127
+packaging==24.2
+pandas==2.2.3
+peft==0.14.0
+pillow==11.1.0
+propcache==0.3.0
+protobuf==6.30.1
+psutil==7.0.0
+pyarrow==19.0.1
+pydantic==2.10.6
+pydantic_core==2.27.2
+pynvml==12.0.0
+python-dateutil==2.9.0.post0
+pytz==2025.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rouge==1.0.1
+safetensors==0.5.3
+sentencepiece==0.2.0
+six==1.17.0
+sympy==1.13.1
+threadpoolctl==3.6.0
+tokenicer==0.0.4
+tokenizers==0.21.1
+torch==2.6.0
+tqdm==4.67.1
+transformers==4.47.1
+triton==3.2.0
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+xxhash==3.5.0
+yarl==1.18.3
+zstandard==0.23.0