LLama 2
Llama 2 encompasses a range of generative text models, both pretrained and fine-tuned, with sizes from 7 billion to 70 billion parameters. Below you can find and download LLama 2 specialized versions of these models, known as Llama-2-Chat, tailored for dialogue scenarios. When compared against open-source chat models on various benchmarks, Llama-2-Chat excels. Moreover, in terms of helpfulness and security, they match the standards set by widely recognized closed-source models such as ChatGPT and PaLM.
All three model sizes are available on HuggingFace for download:
Model | Llama2 | Llama2-hf | Llama2-chat | Llama2-chat-hf |
---|---|---|---|---|
7B | Link | Link | Link | Link |
13B | Link | Link | Link | Link |
70B | Link | Link | Link | Link |
LLama 3
This collection hosts the transformers and original repos of the Meta Llama 3 on HF:
Link |
---|
meta-llama/Meta-Llama-3-8B |
meta-llama/Meta-Llama-3-8B-Instruct |
meta-llama/Meta-Llama-3-70B-Instruct |
meta-llama/Meta-Llama-3-70B |
meta-llama/Meta-Llama-Guard-2-8B |
Let me know if there’s anything else you need!
Ollama
Run, create, and share large language models with Ollama.
Download Ollama for macOS.