Simon Willison on Nostr: DeepSeek released a whole family of inference-scaling / "reasoning" models today, ...
DeepSeek released a whole family of inference-scaling / "reasoning" models today, including distilled variants based on Llama and Qwen
Here are my notes on the new models, plus how I ran DeepSeek-R1-Distill-Llama-8B on my Mac using Ollama and LLM
https://simonwillison.net/2025/Jan/20/deepseek-r1/Published at
2025-01-20 15:22:35Event JSON
{
"id": "4e8808d8294ce1b0684d52c1d4ca51585533d93dce0b46af15c9bae445f8d31d",
"pubkey": "8b0be93ed69c30e9a68159fd384fd8308ce4bbf16c39e840e0803dcb6c08720e",
"created_at": 1737386555,
"kind": 1,
"tags": [
[
"proxy",
"https://fedi.simonwillison.net/users/simon/statuses/113861365293284267",
"activitypub"
]
],
"content": "DeepSeek released a whole family of inference-scaling / \"reasoning\" models today, including distilled variants based on Llama and Qwen\n\nHere are my notes on the new models, plus how I ran DeepSeek-R1-Distill-Llama-8B on my Mac using Ollama and LLM\n\nhttps://simonwillison.net/2025/Jan/20/deepseek-r1/",
"sig": "553d35e6c10dac70723160d3b05bed2841fc2609277ab3acf555525b3e5b217be9f308716e60f397a883f3a3cc27e6b60bad99cb4fbcefdbbfbb5c191dc5b8c6"
}
