中转站推荐 中转站推荐 地址 2dou.net 超低倍率 支持生图 视频(codex gemini claude code grok等模型) 点击进行跳转
公告 PriceAI QQ 交流群已开放 / 欢迎进群交流功能建议、产品想法、数据问题和使用反馈
土豆AI聚合资源、商品与社区聚合平台https://2dou.org/
AI快讯 / AI 开源项目

Korean-llm-v3

Build and run a Korean-specialized 1.09B-parameter LLM from scratch, with PyTorch and 9GB VRAM optimized inference.

AI 开源项目版本发布
原文来源AI 开源 Releases
查看官方原文

Build and run a Korean-specialized 1.09B-parameter LLM from scratch, with PyTorch and 9GB VRAM optimized inference.

RELATED SIGNALS

同厂商与同频道动态

自动关联
版本发布

cachellm

Cut token costs by caching LLM responses locally for OpenAI-compatible providers, eliminating duplicate API calls.

版本发布

llm-eval-harness

A tiny, dependency-free Python harness for scoring LLM answers against a gold set (exact / contains / numeric matching, CI-friendly).

版本发布

ha-ai-pool

Home Assistant integration: pool AI providers for ai_task, conversation, TTS and STT with quota rotation and error-aware failover

版本发布

ai-agents.nvim

One picker for every AI coding agent in Neovim - Claude Code, Codex, Copilot, opencode, Gemini and API models - with a single accept/reject flow for the changes they propose

版本发布

pi-omniroute

OmniRoute provider extension for pi — self-hosted gateway routing 350+ AI providers (Claude, GPT, Gemini, DeepSeek, …) with quota-aware auto-fallback and token compression, exposed as an OpenAI-compatible provider.

版本发布

tokcodec

Token codec for AI coding tools: same signal, 30–95% fewer tokens. Works with Claude Code via npx tokcodec install.