├── LICENSE ├── README.md ├── README_en.md ├── config ├── deepspeed_config.json ├── deepspeed_zero3_config.json ├── llama_13b_config.json ├── llama_30b_config.json ├── llama_65b_config.json └── llama_7b_config.json ├── generate.py ├── llama_dialogue.py ├── llama_gradio.py ├── llama_infer.py ├── llama_server.py ├── model ├── llama.py ├── norm.py ├── rope.py └── tokenize.py ├── prompts.txt └── utils.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/README.md -------------------------------------------------------------------------------- /README_en.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/README_en.md -------------------------------------------------------------------------------- /config/deepspeed_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/deepspeed_config.json -------------------------------------------------------------------------------- /config/deepspeed_zero3_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/deepspeed_zero3_config.json -------------------------------------------------------------------------------- /config/llama_13b_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/llama_13b_config.json -------------------------------------------------------------------------------- /config/llama_30b_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/llama_30b_config.json -------------------------------------------------------------------------------- /config/llama_65b_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/llama_65b_config.json -------------------------------------------------------------------------------- /config/llama_7b_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/config/llama_7b_config.json -------------------------------------------------------------------------------- /generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/generate.py -------------------------------------------------------------------------------- /llama_dialogue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/llama_dialogue.py -------------------------------------------------------------------------------- /llama_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/llama_gradio.py -------------------------------------------------------------------------------- /llama_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/llama_infer.py -------------------------------------------------------------------------------- /llama_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/llama_server.py -------------------------------------------------------------------------------- /model/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/model/llama.py -------------------------------------------------------------------------------- /model/norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/model/norm.py -------------------------------------------------------------------------------- /model/rope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/model/rope.py -------------------------------------------------------------------------------- /model/tokenize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/model/tokenize.py -------------------------------------------------------------------------------- /prompts.txt: -------------------------------------------------------------------------------- 1 | What do you think of OpenAI organization? -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ProjectD-AI/llama_inference/HEAD/utils.py --------------------------------------------------------------------------------