HUGE 🔥 Llama 2 with 32K Context Length

Together AI - "Today, we’re releasing LLaMA-2-7B-32K, a 32K context model built using Position Interpolation and Together AI’s data recipe and system optimizations, including FlashAttention-2. Fine-tune the model for targeted, long-context tasks—such as multi-document understanding, summarization, and QA—and run inference and fine-tune on 32K context with up to 3x speedup. "

Announcement - https://together.ai/blog/llama-2-7b-32k
Hugging Face Model Hub - https://huggingface.co/togethercomputer/LLaMA-2-7B-32K
Together's Model Playground - https://api.together.ai/ (Free 5K Credits)


❤️ If you want to support the channel ❤️
Support here:
Patreon …

context data document understanding inference llama llama 2 recipe summarization together understanding