DeepSeek-V4-Flash-0731
From the source
huggingface.coPublisher’s summary
DeepSeek retrains its flash tier of V4 for coding, agents and tool use — 284B total parameters, 13B active, and a 1M-token context window.
DeepSeek retrains its flash tier of V4 for coding, agents and tool use — 284B total parameters, 13B active, and a 1M-token context window.