📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
agent llm rag tutorial
accelerate
aiofiles
aiohttp
aiosignal
anyio
bitsandbytes
fastapi hello-agents
httpx
httpx-sse
+ 22 more Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
agent ai deepseek fine-tuning gemma gpt instruction-tuning large-language-models llama llama3 llm lora moe nlp peft qlora quantization qwen rlhf transformers
accelerate
av
datasets
einops
fastapi fire
gradio
hf-transfer
matplotlib modelscope
+ 24 more 《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
agent agent-memory ai-agent book coding-agent context-engineering large-language-models llm mcp multi-agent multimodal rag reinforcement-learning
accelerate
openai
peft
torch transformers accelerate
bitsandbytes
datasets
huggingface-hub
peft
torch trackio
transformers trl
accelerate
bitsandbytes
cut_cross_entropy
datasets
hf_transfer
huggingface_hub
peft
protobuf
sentencepiece
soundfile
+ 11 more datasets
librosa
peft
snac
soundfile
torch torchaudio
transformers trl
unsloth
accelerate
bitsandbytes
cut_cross_entropy
datasets
hf_transfer
huggingface_hub
librosa
peft
protobuf
sentencepiece
+ 13 more accelerate
datasets
openai
peft
pytest torch transformers trl
accelerate
datasets
numpy peft
torch tqdm
transformers trl
vllm
wandb
Show less 微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。
agent-framework data-analysis deep-research deep-search llms multi-agent-system nlp public-opinion-analysis python3 sentiment-analysis
accelerate
datasets
numpy pandas peft
safetensors
scikit-learn
torch tqdm
transformers accelerate
bitsandbytes
datasets
numpy pandas peft
scikit-learn
sentence-transformers
torch tqdm
+ 4 more Making large AI models cheaper, faster and more accessible
ai big-model data-parallelism deep-learning distributed-computing foundation-models heterogeneous-training hpc inference large-scale model-parallelism pipeline-parallelism
bitsandbytes
click
contexttimer
diffusers
einops
fabric
fastapi galore_torch
google
ninja
+ 18 more OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
ai assistant chatgpt discord-bot language-model machine-learning nextjs python rlhf
PyYAML accelerate
bitsandbytes
datasets
deepspeed
evaluate
fastlangid
flash_attn
gdown
langcodes
+ 17 more mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
accelerate
datasets
gguf
huggingface_hub
nvidia-ml-py
peft
pydantic pyyaml sentencepiece
torch + 6 more See, hear, and interact on your local devices.
minicpm minicpm-o minicpm-v multi-modal
Pillow
accelerate
addict
aiosignal
decord
deepspeed
editdistance
einops
fairscale
flash-attn
+ 38 more [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
chatbot chatgpt foundation-models gpt-4 instruction-tuning llama llama-2 llama2 llava multi-modality multimodal vision-language-model visual-language-learning
accelerate
bitsandbytes
einops
einops-exts
fastapi gradio
gradio_client
httpx
markdown2[all]
numpy + 15 more Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
evaluation hacktoberfest hacktoberfest2025 langchain llama-index llm llm-evaluation llm-observability llmops open-source openai playground prompt-engineering
accelerate
datasets
flask
gunicorn
huggingface_hub[hf_xet]
peft
presidio-analyzer
scikit-learn
spacy
torch + 4 more Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
inpainting lama latent-diffusion mat pytorch stable-diffusion zits
Pillow
accelerate
controlnet-aux
diffusers
easydict
fastapi gradio
huggingface_hub
loguru
omegaconf
+ 17 more Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
whisper
PyQt6
PyQt6-Qt6
PyQt6-sip
accelerate
bitsandbytes
certifi
cmake
coverage
ctranslate2
cuda-bindings
+ 44 more Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
beit beit-3 bitnet deepnet document-ai foundation-models kosmos kosmos-1 layoutlm layoutxlm llm minilm mllm multimodal nlp pre-trained-model textdiffuser trocr unilm xlm-e
accelerate
auto-gptq
bitsandbytes
datasets
deepspeed
einops
evaluate
fairscale
fire
fraction
+ 23 more Jinja2
MarkupSafe
Pillow
PyYAML Pygments
accelerate
aiofiles
aiohttp
aiosignal
altair
+ 123 more accelerate
auto-gptq
datasets
deepspeed
einops
evaluate
fire
gradio
jsonlines
jupyterlab
+ 20 more 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
adapter diffusion fine-tuning llm lora parameter-efficient-learning peft python pytorch transformers
accelerate
bitsandbytes
datasets
numpy packaging
peft
psutil
pytest pyyaml safetensors
+ 8 more Translate the video from one language to another and embed dubbing & subtitles.
speech-to-text stt subtitle-translation text-to-speech tts video-transition
WeTextProcessing
absl-py
accelerate
addict
aenum
aiofiles
aiohappyeyeballs
aiohttp
aiosignal
alibabacloud-alimt20181012
+ 258 more A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
accelerate
blessed
build
colorlog
datasets
fastapi fire
langchain
ninja
peft
+ 11 more Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.
Jinja2
MarkupSafe
PyYAML Pygments
absl-py
accelerate
aiohappyeyeballs
aiohttp
aiosignal
annotated-types
+ 91 more Train your AI self, amplify you, bridge the world
aiohttp
aiomysql
async-timeout
asyncio
charset-normalizer
chromadb
datasets
flask
flask-pydantic
flask-sock
+ 33 more Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
agent ai automation data-mining data-science development llm research
accelerate
datasets
flask
flask-cors
huggingface_hub
loguru
numpy opencompass
pandas peft
+ 11 more The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
text2music
--extra-index-url
accelerate
diffusers
diskcache
einops
fastapi flash-attn
gradio
lightning
loguru
+ 34 more Llama中文社区,实时汇总最新Llama学习资料,构建最好的中文Llama大模型开源生态,完全开源可商用
agent llama llama4 llm pretraining rl
accelerate
bitsandbytes
datasets
deepspeed
evaluate
gekko
gradio
numpy packaging
pandas + 14 more