Alternatives and similar repositories for zero-lora

Users that are interested in zero-lora are comparing it to the libraries listed below

• ziwang-com / chinese-StableVicuna
  全球首个StableVicuna中文优化版。
  ☆63Updated 2 years ago
• CrazyBoyM / llama2-Chinese-chat
  首个llama2 13b 中文版模型 （Base + 中文对话SFT，实现流畅多轮人机自然语言交互)
  ☆91Updated 2 years ago
• SUSTech-IDEA / SUS-Chat
  SUS-Chat: Instruction tuning done right
  ☆49Updated last year
• xverse-ai / XVERSE-65B
  XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.
  ☆140Updated last year
• zzlgreat / smart_agent
  ☆106Updated last year
• LC1332 / Haruhi-2-Dev
  Just for debug
  ☆56Updated last year
• chu-tianxiang / vllm-gptq
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆132Updated last year
• pleisto / yuren-baichuan-7b
  基于baichuan-7b的开源多模态大语言模型
  ☆72Updated last year
• SomeoneKong / llm_long_context_bench202405
  ☆30Updated last year
• ziwang-com / AGM
  AGM阿格姆：AI基因图谱模型，从token-weight权重微粒角度，探索AI模型，GPT\LLM大模型的内在运作机制。
  ☆29Updated 2 years ago
• QwenLM / vllm-gptq
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆137Updated 9 months ago
• StarRing2022 / ChatGPTX-Uni
  实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案，LLM-Base+LLM-X+Alpaca，初期，LLM-Base为Chatglm6B底座模型，LLM-X是LLAMA增强模型。该方案简易高效，目标是使此类语言模型能够低能耗广泛部署，并最…
  ☆117Updated 2 years ago
• shootime2021 / APUS-xDAN-4.0-moe
  Its an open source LLM based on MOE Structure.
  ☆58Updated last year
• CrazyBoyM / CodeLLaMA-chat
  CodeLLaMA 中文版 - 代码生成助手，huggingface累积下载2w+次
  ☆45Updated last year
• vxfla / kanchil
  Kanchil（鼷鹿）是世界上最小的偶蹄目动物，这个开源项目意在探索小模型（6B以下）是否也能具备和人类偏好对齐的能力。
  ☆113Updated 2 years ago
• K024 / chatglm-q
  Another ChatGLM2 implementation for GPTQ quantization
  ☆54Updated last year
• OpenLMLab / scaling-rope
  code for Scaling Laws of RoPE-based Extrapolation
  ☆73Updated last year
• Chinese-Tiny-LLM / Chinese-Tiny-LLM
  ☆231Updated last year
• WangRongsheng / Aurora
  The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"
  ☆266Updated last year
• yangjianxin1 / unsloth
  Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
  ☆29Updated last year
• CLUEbenchmark / SuperCLUE-RAG
  中文原生检索增强生成测评基准
  ☆122Updated last year
• OpenLMLab / ChatZoo
  Light local website for displaying performances from different chat models.
  ☆87Updated last year
• CLUEbenchmark / SuperCLUE-Llama2-Chinese
  Llama2开源模型中文版-全方位测评，基于SuperCLUE的OPEN基准 | Llama2 Chinese evaluation with SuperCLUE
  ☆127Updated 2 years ago
• llm-factory / imitater
  Imitate OpenAI with Local Models
  ☆89Updated last year
• ArtificialZeng / llama3_explained
  the newest version of llama3，source code explained line by line using Chinese
  ☆22Updated last year
• piDack / chat_zhenhuan
  使用甄嬛语料微调的chatglm
  ☆86Updated 2 years ago
• ssbuild / deep_training
  deep learning
  ☆149Updated 4 months ago
• ClosedCharacter / Peach
  我们是第一个完全可商用的角色大模型。
  ☆40Updated last year
• AtomEcho / AtomBulb
  旨在对当前主流LLM进行一个直观、具体、标准的评测
  ☆95Updated 2 years ago
• Minami-su / character_AI_open
  Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.
  ☆134Updated 8 months ago