Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens
Source
qwenlm.github.io
Date
Why it matters
Open-source Qwen2.5-7B and 14B models now handle 1M-token contexts
Includes inference framework support for the million-token release
Follows earlier Qwen2.5-Turbo upgrade to one-million-token context
Key quotes
“We're releasing two new checkpoints, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time we've upgraded our opensource Qwen models to handle 1M-token contexts.”
Transcript
Tech Report HuggingFace ModelScope Qwen Chat HuggingFace Demo ModelScope Demo DISCORD Introduction Two months after upgrading Qwen2.5-Turbo to support context length up to one million tokens, we are back with the open-source Qwen2.5-1M models and the corresponding inference framework support. Here’s what you can expect from this release: Opensource Models: We’re releasing two new checkpoints, Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, marking the first time we’ve upgraded our opensource Qwen models to handle 1M-token contexts.