Hackernews posts about Qwen2.5-7B

Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data (itsmeduncan.com)

9 points by itsmeduncan 11 days ago | discuss
I ran a Hormuz Crisis emergent SIM: AIs started lying to hide a stalemate

6 points by vinserello 14 days ago | 2 comments
Show HN: Doxa – Open-source emergent simulator for geopolitical scenarios (github.com)

2 points by dinarino 12 days ago | discuss
Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs (cinegraphs.ai)

101 points by graphpilled 3 months ago | 20 comments
Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M (simonwillison.net)

98 points by simonw over 1 year ago | 2 comments
Autopen: Branching LLM editor demo with DeepSeek's Qwen2.5-7B distill of R1 [video] (www.youtube.com)

2 points by anewhnaccount2 about 1 year ago | discuss
We built an O(1) KV Cache for LLMs (Qwen2.5-7B Colab inside) (colab.research.google.com)

1 points by SPLLC about 1 month ago | discuss
Document poisoning in RAG systems: How attackers corrupt AI's sources (aminrj.com)

155 points by aminerj about 2 months ago | 48 comments
Show HN: ZSE – Open-source LLM inference engine with 3.9s cold starts (github.com)

58 points by zyoralabs 2 months ago | 9 comments
Show HN: Local task classifier and dispatcher on RTX 3080 (github.com)

26 points by Shubham_Amb 3 months ago | 2 comments
Show HN: OpenHarness Open-source terminal coding agent for any LLM (github.com)

7 points by wangzhijie about 1 month ago | 1 comments
Show HN: PicoFlow – a minimal Python workflow for LLM agents

2 points by shijizhi_1919 3 months ago | discuss
Show HN: Linguistic RL – A 7B model discovers Occam's Razor through reflection (github.com)

2 points by drawson5570 6 months ago | discuss
Show HN: ZSE – Single-file LLM engine with dual INT4 kernels (github.com)

1 points by zyoralabs 2 months ago | discuss