Awesome LLM is a comprehensive collection of resources in the field of Large Language Models, providing researchers and developers with essential references and learning materials.
Resource Categories
📄 Research Papers
- Foundation architectures (Transformer, GPT series, BERT)
- Training techniques (Pre-training, Fine-tuning, RL)
- Evaluation methods and benchmarks
- Application research papers
🛠️ Tools
- Training frameworks (DeepSpeed, FairScale)
- Inference engines (vLLM, TensorRT-LLM)
- Fine-tuning tools (LoRA, PEFT)
- Evaluation frameworks
📊 Datasets
- Pre-training datasets (Common Crawl, The Pile)
- Instruction datasets (Alpaca, ShareGPT)
- Evaluation benchmarks (MMLU, GLUE)
🤖 Open Source Models
- Base models (LLaMA, Falcon)
- Fine-tuned models (Vicuna, ChatGLM)
- Code models (CodeLlama)
- Multimodal models (LLaVA)
Technical Areas
Covers model architectures, training techniques, fine-tuning methods, and inference optimization. Includes applications in NLP, code generation, multimodal tasks, and scientific research.