Pinned Repositories
gdGPT
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
haystack
:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
haystack-chinese
:mag: 基于deepsetAI的开源项目haystack进行修改，使其支持中文场景下的任务
mc112611
Config files for my GitHub profile.
mojo
The Mojo Programming Language
open-interpreter
OpenAI's Code Interpreter in your terminal, running locally
ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
SRP
Sturctured pruning algorithm for pruning Transformer
mc112611's Repositories
mc112611/haystack-chinese
:mag: 基于deepsetAI的开源项目haystack进行修改，使其支持中文场景下的任务
mc112611/mc112611
Config files for my GitHub profile.
mc112611/mojo
The Mojo Programming Language
mc112611/open-interpreter
OpenAI's Code Interpreter in your terminal, running locally
mc112611/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.