shiyemin / light-hf-proxy
A light proxy solution for HuggingFace hub.
☆46Updated last year
Alternatives and similar repositories for light-hf-proxy:
Users that are interested in light-hf-proxy are comparing it to the libraries listed below
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- Light local website for displaying performances from different chat models.☆85Updated last year
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆110Updated 2 months ago
- ☆25Updated 3 months ago
- Gaokao Benchmark for AI☆105Updated 2 years ago
- ☆36Updated 4 months ago
- ☆78Updated 8 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆36Updated 4 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆36Updated last year
- XVERSE-MoE-A4.2B: A multilingual large language model developed by XVERSE Technology Inc.☆36Updated 8 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- A more efficient GLM implementation!☆55Updated last year
- the newest version of llama3，source code explained line by line using Chinese☆22Updated 9 months ago
- 1.4B sLLM for Chinese and English - HammerLLM🔨☆44Updated 9 months ago
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- This repository provides an implementation of the paper "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Co…☆52Updated 3 weeks ago
- GLM Series Edge Models☆127Updated 3 weeks ago
- ☆32Updated 8 months ago
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆47Updated last year
- ☆105Updated last year
- 本项目旨在对大量文本文件进行快速编码检测和转换以辅助mnbvc语料集项目的数据清洗工作☆56Updated 3 months ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆70Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆55Updated 9 months ago
- 我们是第一个完全可商用的角色大模型。☆38Updated 5 months ago
- ☆27Updated last year
- Chinese CLIP models with SOTA performance.☆53Updated last year
- zero零训练llm调参☆31Updated last year
- 纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，☆45Updated last year
- 百度QA100万数据集☆47Updated last year
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆45Updated 7 months ago