The open-source AI models you can fine-tune, distill and deploy anywhere. Choose from our collection of models: Llama 3.1, Llama 3.2, Llama 3.3.

Llama (Large Language Model Meta AI, formerly stylized as LLaMA) is a family of large language models (LLMs) released by Meta AI starting in February 2023. [2][3] The latest version is Llama 4, released in April 2025. [4] Llama models are trained at different parameter sizes, ranging between 1B and 405B. [5] .

LightAutoML (LAMA) is an AutoML framework by Sber AI Lab. It provides automatic model creation for the following tasks: binary classification; multiclass classification; regression; Current version of the package handles datasets that have independent samples in each row. I.e. each row is an object with its specific features and target ...

2023年2月27日 · We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets.

以 GPT-3 为代表的大语言模型 (Large language models, LLMs) 在海量文本集合上训练，展示出了惊人的涌现能力以及零样本迁移和少样本学习能力。 GPT-3 把模型的量级缩放到了 175B，也使得后面的研究工作继续去放大语言模型的量级。 大家好像有一个共识，就是： 模型参数量级的增加就会带来同样的性能提升。 但是事实确实如此吗？ 最近的 "Training Compute-Optimal Large Language Models [1] " 这篇论文提出一种 缩放定律 (Scaling Law)： 训练大语言模型时，在计 …

We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets.

2023年2月24日 · As part of Meta’s commitment to open science, today we are publicly releasing LLaMA (Large Language Model Meta AI), a state-of-the-art foundational large language model designed to help researchers advance their work in this subfield of AI.

LightAutoML (LAMA) allows you create machine learning models using just a few lines of code, or build your own custom pipeline using ready blocks. It supports tabular, time series, image and text data.

llama2 是meta最新开源的语言大模型，训练数据集2万亿token，上下文长度是由llama的2048扩展到4096，可以理解和生成更长的文本，包括7B、13B和70B三个模型，在各种基准集的测试上表现突出，最重要的是，该模型可用于研究和商业用途。 语言模型是对文本进行推理。 由于文本是字符串，但对模型来说，输入只能是数字，所以就需要将文本转成用数字来表达。 最直接的想法，就是类似查字典，构造一个字典，包含文本中所有出现的词汇，比如中文，可以每个字作为词典 …

This repo contains a script for converting a LaMa (aka cute, fuzzy 🦙) model to Apple's Core ML model format. More specifically, it converts the implementation of LaMa from Lama Cleaner. This repo also includes a simple example of how to use the …