Hackernews posts about Qwen2.5-7B

RSS feed for Qwen2.5-7B

01
newShow HN: Putaway – sorts your Mac's Downloads into the folders you havegithub.com
▲ 3yashrajpandey 22d discuss
02
newShow HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai
▲ 101graphpilled 272d 💬 20
03
newQwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net
▲ 98simonw 650d 💬 2
04
newCivic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com
▲ 9itsmeduncan 196d discuss
05
newLocal Autonomous Security Agent-QWEN2.5-7B+MCP Agent Loophuggingface.co
▲ 2automajicly 183d discuss
06
newAutopen: Branching LLM editor demo with DeepSeek's Qwen2.5-7B distill of R1 [video]www.youtube.com
▲ 2anewhnaccount2 636d discuss
07
newWe built an O(1) KV Cache for LLMs (Qwen2.5-7B Colab inside)colab.research.google.com
▲ 1SPLLC 221d discuss
08
newDocument poisoning in RAG systems: How attackers corrupt AI's sourcesaminrj.com
▲ 155aminerj 240d 💬 48
09
newShow HN: ZSE – Open-source LLM inference engine with 3.9s cold startsgithub.com
▲ 58zyoralabs 255d 💬 9
10
newShow HN: Local task classifier and dispatcher on RTX 3080github.com
▲ 26Shubham_Amb 275d 💬 2
11
newShow HN: OpenHarness Open-source terminal coding agent for any LLMgithub.com
▲ 7wangzhijie 220d 💬 1
12
newAsk HN: How is GPU power draw measured at scale?
▲ 6anax32 134d 💬 2
13
newI ran a Hormuz Crisis emergent SIM: AIs started lying to hide a stalemate
▲ 6vinserello 199d 💬 2
14
newShow HN: Doxa – Open-source emergent simulator for geopolitical scenariosgithub.com
▲ 2dinarino 197d discuss
15
newShow HN: PicoFlow – a minimal Python workflow for LLM agents
▲ 2shijizhi_1919 287d discuss
16
newShow HN: Linguistic RL – A 7B model discovers Occam's Razor through reflectiongithub.com
▲ 2drawson5570 365d discuss
17
newShow HN: ZSE – Single-file LLM engine with dual INT4 kernelsgithub.com
▲ 1zyoralabs 250d discuss