Liquid AI 发布 LFM2.5-2.6B-MLX-nvfp4 模型
Liquid AI 在 Hugging Face 上发布了 LFM2.5-2.6B-MLX-nvfp4,这是一个针对 Apple Silicon 优化的 MLX 导出模型,基于 LFM2.5-2.6B,采用混合架构,支持长上下文,参数 2.6B,精度 NVFP4,大小 1.53 GB,上下文长度 131072,支持 16 种语言,许可证为 LFM 1.0。
证据来源
查看来源摘录
Liquid AI LiquidAI/LFM2.5-2.6B-MLX-nvfp4 LiquidAI/LFM2.5-2.6B-MLX-nvfp4 https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4
查看来源摘录
LiquidAI/LFM2.5-2.6B-MLX-nvfp4 · Hugging Face Hugging Face (https://huggingface.co/) Models (https://huggingface.co/models) Datasets (https://huggingface.co/datasets) Spaces (https://huggingface.co/spaces) Buckets new (https://huggingface.co/storage) Docs (https://huggingface.co/docs) Enterprise (https://huggingface.co/enterprise) Pricing (https://huggingface.co/pricing) Website Tasks (https://huggingface.co/tasks) HuggingChat (https://huggingface.co/chat) Collections (https://huggingface.co/collections) Languages (https://huggingface.co/languages) Organizations (https://huggingface.co/organizations) Community Blog (https://huggingface.co/blog) Posts (https://huggingface.co/posts) Daily Papers (https://huggingface.co/papers) Hardware (https://huggingface.co/hardware) Learn (https://huggingface.co/learn) Discord (https://huggingface.co/join/discord) Forum (https://discuss.huggingface.co/) GitHub (https://github.com/huggingface) Solutions Team & Enterprise (https://huggingface.co/enterprise) Hugging Face PRO (https://huggingface.co/pro) Enterprise Support (https://huggingface.co/support) Inference Providers (https://huggingface.co/inference/models) Inference Endpoints (https://huggingface.co/inference-endpoints) Storage Buckets (https://huggingface.co/storage) Log In (https://huggingface.co/login) Sign Up (https://huggingface.co/join) (https://huggingface.co/LiquidAI) LiquidAI (https://huggingface.co/LiquidAI) / LFM2.5-2.6B-MLX-nvfp4 (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4) like 2 Follow Liquid AI 4.91k Text Generation (https://huggingface.co/models?pipeline_tag=text-generation) MLX (https://huggingface.co/models?library=mlx) Safetensors (https://huggingface.co/models?library=safetensors) 16 languages lfm2 (https://huggingface.co/models?other=lfm2) liquid (https://huggingface.co/models?other=liquid) lfm2.5 (https://huggingface.co/models?other=lfm2.5) edge (https://huggingface.co/models?other=edge) conversational (https://huggingface.co/models?other=conversational) 4-bit precision (https://huggingface.co/models?other=4-bit) License: lfm1.0 Model card (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4) Files Files and versions xet (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4/tree/main) Community (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4/discussions) Deploy Copy to bucket new Use this model Instructions to use LiquidAI/LFM2.5-2.6B-MLX-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started. Libraries MLX (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4?library=mlx) How to use LiquidAI/LFM2.5-2.6B-MLX-nvfp4 with MLX: # Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("LiquidAI/LFM2.5-2.6B-MLX-nvfp4") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) Notebooks Google Colab (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4/colab) Kaggle (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4/kaggle) Local Apps Settings (https://huggingface.co/settings/local-apps) LM Studio (lmstudio://open_from_hf?model=LiquidAI/LFM2.5-2.6B-MLX-nvfp4) Pi (https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-nvfp4?local-app=pi) How to use LiquidAI/LFM2.5-2.6B-MLX-nvfp4 with Pi: Start the MLX server # Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "LiquidAI/LFM2.5-2.6B-MLX-nvfp4"Configure the model in Pi # Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "LiquidAI/LFM2.5-2.6B-MLX-nvf
来自 星盘大模型百科