Hugging Face 热门模型第 30 名:LiquidAI/LFM3-1.7B,155 赞,近期下载 6311 次。
标签:transformers, safetensors, lfm3, text-generation, liquid, edge, conversational, custom_code, en, ar, zh, fr
README:
<img
src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/liquid-ai-banner.webp"
alt="Liquid AI"
style="width: 100%; max-width: 100%; height: auto; display: block; margin: 0;"
/>
API
Try
Docs
Blog
LFM3-1.7B
LFM3-1.7B 是一个面向本地代理和专用应用的文本模型,基于我们全新的三混合架构。
- 代理训练: 针对 Hermes Agent、Pi 和 OpenClaw 等代理框架进行了后训练,支持 256K token 的上下文窗口。
- 专为边缘设备设计: 在 4-bit 精度下,仅需约 1 GB 内存,因此可运行于任何手机或笔记本电脑上。
- 易于专业化定制: 通过单 GPU 快速微调,将模型适配到你的领域、格式和工具中。
有关 LFM3 系列的更多信息,请参阅我们的发布博客文章。
模型详情
LFM3 系列包括基础模型、文本模型、视觉模型、音频模型、全能模型(omni)和决策模型。
属性
规格
检查点
后训练的纯文本语言模型
参数量
1.73B
架构
24 层:13 个门控短卷积、5 个滑动窗口注意力、6 个全局注意力
上下文长度
256K tokens(输入 + 输出)
词汇表
128,000 tokens
语言
英语、阿拉伯语、中文、法语、德语、意大利语、日语、韩语、葡萄牙语、西班牙语、越南语、泰语、印尼语、印地语、俄语、波兰语
许可证
LFM Open License v1.0
LFM3-1.7B 专为本地代理、工具调用、结构化输出和领域特定微调而设计。对于知识密集型任务,建议使用检索或搜索功能。由于其规模较小,不建议用于代理式编码或复杂的多步推理。
推理
为你的推理框架和硬件选择合适的检查点变体。
检查点
框架
D
查看原文
Hugging Face 热门模型第 30 名:LiquidAI/LFM3-1.7B,155 赞,近期下载 6311 次。
标签:transformers, safetensors, lfm3, text-generation, liquid, edge, conversational, custom_code, en, ar, zh, fr
README:
<img
src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/liquid-ai-banner.webp"
alt="Liquid AI"
style="width: 100%; max-width: 100%; height: auto; display: block; margin: 0;"
/>
API
Try
Docs
Blog
LFM3-1.7B
LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.
- Agentic training: post-trained for agentic harnesses such as Hermes Agent, Pi, and OpenClaw, with a 256K-token context window.
- Designed for the edge: at 4-bit precision, it takes about 1 GB of memory, so it fits on any phone or laptop.
- Made to be specialized: adapt the model to your domains, formats, and tools via quick single-GPU fine-tuning.
Find more information about the LFM3 family in our release blog post.
Model details
The LFM3 family includes base, text, vision, audio, omni, and decision models.
Property
Specification
Checkpoint
Post-trained, text-only language model
Parameters
1.73B
Architecture
24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
Context length
256K tokens (input + output)
Vocabulary
128,000 tokens
Languages
English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
License
LFM Open License v1.0
LFM3-1.7B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.
Inference
Choose a checkpoint variant for your inference framework and hardware.
Checkpoint
Framework
D
原文版权归 Hugging Face 热门模型 及原作者所有,本站转载仅供阅读。如需删除,请联系 support@aisa.one。