Tag: llama
-
Simon Willison’s Weblog: Anomalous Tokens in DeepSeek-V3 and r1
Source URL: https://simonwillison.net/2025/Jan/26/anomalous-tokens-in-deepseek-v3-and-r1/#atom-everything Source: Simon Willison’s Weblog Title: Anomalous Tokens in DeepSeek-V3 and r1 Feedly Summary: Anomalous Tokens in DeepSeek-V3 and r1 Glitch tokens (previously) are tokens or strings that trigger strange behavior in LLMs, hinting at oddities in their tokenizers or model weights. Here’s a fun exploration of them across DeepSeek v3 and R1.…
-
Simon Willison’s Weblog: Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens
Source URL: https://simonwillison.net/2025/Jan/26/qwen25-1m/ Source: Simon Willison’s Weblog Title: Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens Feedly Summary: Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens Very significant new release from Alibaba’s Qwen team. Their openly licensed (sometimes Apache 2, sometimes Qwen license, I’ve had trouble keeping…
-
Hacker News: Llama.vim – Local LLM-assisted text completion
Source URL: https://github.com/ggml-org/llama.vim Source: Hacker News Title: Llama.vim – Local LLM-assisted text completion Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text describes a local LLM-assisted text completion plugin named llama.vim designed for use within the Vim text editor. It provides features such as smart context reuse, performance statistics, and configurations based on…
-
Simon Willison’s Weblog: r1.py script to run R1 with a min-thinking-tokens parameter
Source URL: https://simonwillison.net/2025/Jan/22/r1py/ Source: Simon Willison’s Weblog Title: r1.py script to run R1 with a min-thinking-tokens parameter Feedly Summary: r1.py script to run R1 with a min-thinking-tokens parameter Fantastically creative hack by Theia Vogel. The DeepSeek R1 family of models output their chain of thought inside a …</think> block. Theia found that you can intercept…
-
Hacker News: LLMs Demonstrate Behavioral Self-Awareness [pdf]
Source URL: https://martins1612.github.io/selfaware_paper_betley.pdf Source: Hacker News Title: LLMs Demonstrate Behavioral Self-Awareness [pdf] Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The provided text discusses a study focused on the concept of behavioral self-awareness in Large Language Models (LLMs). The research demonstrates that LLMs can be finetuned to recognize and articulate their learned behaviors, including…
-
Hacker News: Official DeepSeek R1 Now on Ollama
Source URL: https://ollama.com/library/deepseek-r1 Source: Hacker News Title: Official DeepSeek R1 Now on Ollama Feedly Summary: Comments AI Summary and Description: Yes Summary: The text provides an overview of DeepSeek’s first-generation reasoning models that exhibit performance comparable to OpenAI’s offerings across math, code, and reasoning tasks. This information is highly relevant for practitioners in AI and…