llama3

• #411

  Error from "llama-model download --source meta --model-id Llama-4-Scout-17B-16E"

  更新于 2025年12月23日
• #414

  Meta AI: User-Centric, Niche-Focused Upgrades for WhatsApp & Instagram (Community Discussion)

  更新于 2025年12月22日
• #412

  Job hunting

  更新于 2025年12月14日
• #402

  阿斯顿 张 和李沐 先生 你好，我们打算参考 动手学 系列 出版 scala 版本pytorch 的深度学习 图书

  更新于 2025年12月14日
• #356

  Model being very repetitive

  更新于 2025年10月30日
• #392

  sp_model = SentencePieceProcessor() sp_model.Load("/home/imss/zxhhhh/llama-3-8b/tokenizer.model")

  更新于 2025年10月23日
• #404

  LLAMA 3.3 skips instruction

  更新于 2025年9月6日
• #129

  Trying to set a tensor of shape torch.Size([1024, 4096]) in "weight" (which has shape torch.Size([4096, 4096])), this look incorrect.

  更新于 2025年8月6日
• #247

  Llama2 transfer to Llama3

  question更新于 2025年8月6日
• #285

  Llama3.1 405B using FP8 TypeError: couldn't find storage object Float8_e4m3fnStorage

  更新于 2025年7月15日

核心特点

• •llama-models - Central repo for the foundation models including basic utilities, model cards, license and use policies
• •PurpleLlama - Key component of Llama Stack focusing on safety risks and inference time mitigations
• •llama-toolchain - Model development (inference/fine-tuning/safety shields/synthetic data generation) interfaces and canonical implementations
• •llama-agentic-system - E2E standalone Llama Stack system, along with opinionated underlying interface, that enables creation of agentic applications
• •llama-cookbook - Community driven scripts and integrations
• •Visit one of the repos, for example meta-llama/Meta-Llama-3-8B-Instruct.
• •Read and accept the license. Once your request is approved, you'll be granted access to all the Llama 3 models. Note that requests used to take up to one hour to get processed.
• •To use with transformers, the following pipeline snippet will download and cache the weights:
• •Make sure to grant execution permissions to the download.sh script
• •During this process, you will be prompted to enter the URL from the email.