LLM Models Resources 7 Popular LLMs Explained in 7 Minutes - KDnuggets Awesome Free LLM APIs Chinese LLMs Taiwan LLM - Project TAME (TAiwanese Mixture of Experts) GitHub: https://github.com/MiuLab/Taiwan-LLM   HF:  https://huggingface.co/yentinglin   HF:  https://huggingface.co/audreyt   臺灣繁中LLM另一里程碑！Project TAME以5,000億個Token訓練而成並開源釋出 | iThome Project TAME上線！「最台AI」獲輝達算力支援，能懂「很盤」涵義，3大優勢有哪些？|數位時代 BusinessNext TAIDE (台德)- Trustworthy AI Dialogue Engine GitHub: https://github.com/taide-taiwan   HF:  https://huggingface.co/taide   TAIDE | iThome 01.AI - Yi GitHub: https://github.com/01-ai/Yi   HF:  https://huggingface.co/01-ai/   CKIP-Llama-2-7b 是中央研究院詞庫小組(CKIP)開發的開源可商用繁體中文大型語言模型，以商用開源模型Llama-2-7b以及Atom-7b為基礎，再補強繁體中文的處理能力，並對405個可商用的任務檔案同步進行訓練優化，參數量達70億(7 billion)。 GitHub: https://github.com/f901107/CKIP-Llama-2-7b   HF:  https://huggingface.co/spaces/ckiplab/CKIP-Llama-2-7b-chat   Qwen - 阿里雲通義千問 GitHub: https://github.com/QwenLM/Qwen GitHub: https://github.com/QwenLM/Qwen2   HF:  https://huggingface.co/Qwen Doc: https://help.aliyun.com/zh/dashscope/create-a-chat-foundation-model?spm=a2c4g.11186623.0.0.20ea4937azFCan   GLM-4 - 智譜 AI 推出的中文多語言模型 GitHub: https://github.com/THUDM/GLM-4   HF: https://huggingface.co/collections/THUDM/glm-4-665fcf188c414b03c2f7e3b7   Chinese-Mixtral DeepSeek - 深度求索 GitHub: https://github.com/deepseek-ai/DeepSeek-V2 HF: https://huggingface.co/deepseek-ai/DeepSeek-V2     Code LLMs Granite - Open sourcing IBM’s Granite code models H F:  https://huggingface.co/ibm-granite   GitHub: https://github.com/ibm-granite   IBM開源程式開發專用Granite語言模型，效能超越當前多數開源模型 | iThome IBM Granite 3.0 models · Ollama Blog IBM Granite.Code - Visual Studio Marketplace Codestral - Mistral's first generative AI model for code HF:  https://huggingface.co/mistralai/Codestral-22B-v0.1 Mistral AI推出輕量程式撰寫輔助模型 | iThome   Gemini Code Assist - Google 推出的程式編寫助理，可以在 VS Code、JetBrains IDE 上使用。 Evaluation/Monitor PromptBench : A Unified Library for Evaluating and Understanding Large Language Models. AI產品與系統評測中心: AI評測模擬測試題庫.xlsx Opik is an open-source platform for evaluating, testing and monitoring LLM applications. Function Calling LLMs Firefunction-v2 HF:  https://huggingface.co/fireworks-ai/firefunction-v2   Content Safty Google ShieldGemma ShieldGemma則是個安全分類模型，可額外部署在模型的輸入及輸出端，用以過濾有害內容，它主要篩選4大領域的內容，包括仇恨言論、騷擾、裸露的色情內容，以及危險內容。 Hardware Requirements 如何計算 Model 需要多少 GPU VRAM Calculates how much GPU memory you need and how much token/s you can get for any LLM & GPU/CPU LLM RAM Calculator llmfit - A terminal tool that right-sizes LLM models to your system's RAM, CPU, and GPU. CanIRun.ai