Ruilin Zhao's starred repositories
parallel-decoding
Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"
nccl-tests
NCCL Tests
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Pai-Megatron-Patch
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
Llama-Chinese
Llama中文社区,最好的中文Llama大模型,完全开源可商用
Model-References
TensorFlow and PyTorch Reference models for Gaudi(R)
Firefly-LLaMA2-Chinese
Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型
llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
GitHub-Chinese-Top-Charts
:cn: GitHub中文排行榜,各语言分设「软件 | 资料」榜单,精准定位中文好项目。各取所需,高效学习。
Torch-Pruning
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models