搜索 "llm" 找到 29 个结果
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
AirLLM 70B inference with single 4GB GPU
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job traini
LLM Finetuning with peft
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardw
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language M
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory,
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断
字节PyTorch分布式用于超大规模训练LLMs和RLs。
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your ma
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
Visual intelligence for your home.
