Pinned Repositories
bigcode-dataset
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
ColossalAI
Making large AI models cheaper, faster and more accessible
cosinor_rythm_analysis
csghub
CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more. CSGHub是一个开源、可信的大模型资产管理平台,可帮助用户治理LLM和LLM应用生命周期中涉及到的资产(数据集、模型文件、代码等)。CSGHub提供类似私有化的Huggingface功能,以类似OpenStack Glance管理虚拟机镜像、Harbor管理容器镜像以及Sonatype Nexus管理制品的方式,实现对LLM资产的管理。欢迎关注反馈和Star⭐️
DHS-LLM-Workshop
DHS 2023 LLM Workshop by Sourab Mangrulkar
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
human-learning-optimization
HLO:human learning optimization
litgpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
lm-evaluation-harness
A framework for few-shot evaluation of language models.
peiji1981's Repositories
peiji1981/cosinor_rythm_analysis
peiji1981/human-learning-optimization
HLO:human learning optimization
peiji1981/bigcode-dataset
peiji1981/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
peiji1981/ColossalAI
Making large AI models cheaper, faster and more accessible
peiji1981/csghub
CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more. CSGHub是一个开源、可信的大模型资产管理平台,可帮助用户治理LLM和LLM应用生命周期中涉及到的资产(数据集、模型文件、代码等)。CSGHub提供类似私有化的Huggingface功能,以类似OpenStack Glance管理虚拟机镜像、Harbor管理容器镜像以及Sonatype Nexus管理制品的方式,实现对LLM资产的管理。欢迎关注反馈和Star⭐️
peiji1981/DHS-LLM-Workshop
DHS 2023 LLM Workshop by Sourab Mangrulkar
peiji1981/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
peiji1981/litgpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
peiji1981/lm-evaluation-harness
A framework for few-shot evaluation of language models.
peiji1981/PySyft
A library for encrypted, privacy preserving machine learning
peiji1981/rayfed
A multiple parties joint, distributed execution engine based on Ray, to help build your own federated learning frameworks in minutes.
peiji1981/Megatron-LM
Ongoing research training transformer models at scale
peiji1981/NExT-GPT
Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model
peiji1981/Open-Sora
Building your own video generation model like OpenAI's Sora
peiji1981/starcoder
Home of StarCoder: fine-tuning & inference!
peiji1981/TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.