Qihoo360 / 360zhinao
360zhinao
☆280Updated last month
Related projects ⓘ
Alternatives and complementary repositories for 360zhinao
- Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.☆482Updated 3 months ago
- 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☆396Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆121Updated 10 months ago
- CMMLU: Measuring massive multitask language understanding in Chinese☆696Updated this week
- ☆213Updated 5 months ago
- Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】☆184Updated last month
- 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 last year
- BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability☆421Updated last year
- [EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models☆406Updated 7 months ago
- The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.☆436Updated 3 weeks ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆330Updated 2 months ago
- ☆297Updated last year
- ☆217Updated last year
- Baichuan2代码的逐行解析版本,适合小白☆209Updated last year
- ☆347Updated 3 months ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆654Updated last year
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆231Updated this week
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆163Updated last year
- Luotuo Embedding(骆驼嵌入) is a text embedding model, which developed by 李鲁鲁, 冷子昂, 陈启源, 蒟蒻等.☆259Updated last year
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆166Updated 5 months ago
- 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)☆89Updated last year
- An easy-to-use framework for modular RAG☆289Updated this week
- 语言模型中文认知能力 分析☆235Updated last year
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆132Updated 7 months ago
- Llama3-Chinese是以Meta-Llama-3-8B为底座,使用 DORA + LORA+ 的训练方法,在50w高质量中文多轮SFT数据 + 10w英文多轮SFT数据 + 2000单轮自我认知数据训练而来的大模型。☆289Updated 6 months ago
- 通义千问VLLM推理部署DEMO☆437Updated 7 months ago
- ☆263Updated 4 months ago
- A Python Package to Access World-Class Generative Models☆124Updated 4 months ago
- 使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。☆354Updated last year
- 中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)☆581Updated 6 months ago