🤠 Cargo bloat for toolchainstable-x86_64-unknown-linux-gnu🤠 @@ Size breakdown @@-Size 86.15 MB+Size 86.22 MB +74.8 KB-Text Size 26.28 MB+Text Size 26.3 MB +19.48 KB Size difference per crate Note:The numbers below are not 100% accurate, use them as a rough estimate. ...
OpenCompass - OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets. Opik - Opik is an open-source platform for evaluating, testing and monitoring LLM applications. Optimum-Benchmark - A unified multi...
fun - The simplest but powerful way to use large language models (LLMs) in Go. langchaingo - LangChainGo is a framework for developing applications powered by language models. LocalAI - Open Source OpenAI alternative, self-host AI models. Ollama - Run large language models locally. Ollama...
fun - The simplest but powerful way to use large language models (LLMs) in Go. langchaingo - LangChainGo is a framework for developing applications powered by language models. LocalAI - Open Source OpenAI alternative, self-host AI models. Ollama - Run large language models locally. Ollama...
fun - The simplest but powerful way to use large language models (LLMs) in Go. langchaingo - LangChainGo is a framework for developing applications powered by language models. LocalAI - Open Source OpenAI alternative, self-host AI models. Ollama - Run large language models locally. Ollama...
Making LLaMA SEE and Draw with SEED Tokenizer (2 Oct 2023)Yuying Ge, Sijie Zhao, Ziyun Zeng, et al.Yuying Ge, Sijie Zhao, Ziyun Zeng, Yixiao Ge, Chen Li, Xintao Wang, Ying Shan tokenizer InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists (30 Sep 2023...
Faster debug and development with tiny models, tokenizers and datasets (https://github.com/stas00/ml-engineering/blob/master/transformers/make-tiny-models.md) (https://huggingface.co/stas/tiny-random-llama-2) (https://huggingface.co/stas/tiny-random-llama-2/blob/main/make_tiny_model.py) Ma...
[rank0]: File "/mnt/gemininjceph2/geminicephfs/wx-mm-spr-xxxx/zhaochang/MEIJU/Qwen2-VL/LLaMA-Factory/src/llamafactory/train/sft/workflow.py", line 51, in run_sft [rank0]: dataset_module = get_dataset(template, model_args, data_args, training_args, stage="sft", **tokenizer_module...
tokenizers Fast and Customizable Tokenizers 16 msrestazure AutoRest swagger generator Python client runtime. Azure-specific module. 16 pyclipper Cython wrapper for the C++ translation of the Angus Johnson's Clipper library (ver. 6.4.2) 16 optax A gradient processing and optimisation library in JA...
LlamaIndex Toolkits:LlamaHub: A library of data loaders for LLMsgit[Feb 2023] /LlamaIndex CLI: a command line tool to generate LlamaIndex appsref[Nov 2023] /LlamaParse: A unique parsing tool for intricate documentsgit[Feb 2024] From Simple to Advanced RAGref[10 Oct 2023] ...