Liquid Audio - Speech-to-Speech audio models by Liquid AI
-
Updated
Oct 3, 2026 - Python
#
lfm2
Here are 34 public repositories matching this topic...
Running Mixture of Agents on CPU: LFM2.5 Brain (1.2B) + Falcon-R Reasoner (600M) + Tool Caller (90M). CPU-only, 16GB RAM. Lightweight AI Legion.
multilingual lightweight falcon agents moa uv on-device-ai cpu-inference llm llama-cpp mixture-of-agents tool-calling lfm2
-
Updated
Feb 7, 2026 - Python
A hackable library for running and fine-tuning modern transformer models on commodity and alternative GPUs, powered by tinygrad.
-
Updated
Feb 10, 2026 - Python
LFM2-powered research agent | Automated Related Work & citations | Semantic Scholar + arXiv
-
Updated
Jan 9, 2026 - Python
Advanced PDF/Document Translator with interactive comparison. Built on IBM Docling.
python nlp html pdf docs translation ai pdf-converter docx pptx pdf-to-text tables yanolja document-parser huggingface streamlit llm docling qwen3 lfm2
-
Updated
Jan 5, 2026 - Python
Two-layer agentic Earth Observation on satellite-class compute. Fine-tuned LFM2.5-VL perception + tool-calling agent over Sentinel-2 imagery. Galamsey detection in Ghana as the worked example.
-
Updated
May 5, 2026 - Python
ComfyUI nodes for Batch Image Captioning + various Vision-Language (VL) models, including InternVL3.5, Xiaomi MiMo-VL, LiquidAI LFM2-VL, Kwai Keye-VL, AIDC-AI Ovis2.5 and Ovis-U1. Models: Ovis2.5-2B, Ovis2.5-9B, Keye-VL-8B-Preview, MiMo-VL-7B-RL-GGUF, LFM2-VL-450M, LFM2-VL-1.6B, Ovis-U1-3B, Ovis2.5-2B, Ovis2.5-9B, InternVL3_5-1B/2B/4B/8B/14B/38B
computer-vision image-captioning captioning-images ovis caption-generator image-text-retrieval vision-language-model comfyui comfyui-custom-node lfm2 internvl3 xiaomi-mimo keye-vl batch-image-captioning
-
Updated
Aug 29, 2025 - Python
Fine-tuning LFM2-1.2B for Korean-English bidirectional translation. GRPO+COMET & SFT Training, outperforming 4B models.
nlp translation machine-translation kaggle english korean fine-tuning colab-notebook sft huggingface grpo lfm2
-
Updated
Jan 4, 2026 - Jupyter Notebook
Fine-tune LiquidAI LFM2.5 Embedding models for dense retrieval using your own data
-
Updated
Aug 3, 2026 - Python
🎯 The world's first fully internationalized LFM2-350M chat interface with native support for 8 languages!
-
Updated
Oct 3, 2025 - Python
PocketLFM — run Liquid AI's LFM2.5 large language model fully on-device on Android. Offline, private, no cloud. Open-source edge AI via llama.cpp (GGUF). First independent open-source Android app to run LFM2.5 outside Liquid's own Apollo/LEAP.
android kotlin edge-ai jetpack-compose liquid-ai edge-inference llm llama-cpp local-llm gguf offline-ai private-ai small-language-model lfm2 on-device-llm
-
Updated
Jun 22, 2026 - C++
Offline RAG study assistant powered by LFM2-2.6B · Ask questions, get exercises from any PDF textbook · No cloud required
python education pdf language-learning chroma gradio bm25 english-grammar rag study-assistant llm langchain llama-cpp langchain-python local-llm llm-inference local-ai ollama offline-ai lfm2
-
Updated
Apr 20, 2026 - Python
A minimal implementation of Liquid Foundation Model LFM 2.5 2.6B model
-
Updated
Sep 1, 2026 - Python
Blazing fast NPCs with Spatio-Temporal awareness inside Unreal Engine
unreal-engine clip spatio-temporal onnxruntime qdrant whisper-cpp llama-cpp all-minilm-l6-v2 piper-tts lfm2 gpt-oss-120b
-
Updated
Sep 14, 2025 - C++
Fully offline RAG for Android: PDF ingestion, on-device embeddings (ONNX multilingual-e5-small) and grounded chat with LFM2-1.2B-RAG via the LEAP SDK. Kotlin, Jetpack Compose, Hilt, Room, Navigation 3.
android kotlin room pdf offline-first mvvm clean-architecture sentence-embeddings rag vector-search jetpack-compose on-device-ai hilt onnx-runtime llm retrieval-augmented-generation multilingual-e5 lfm2 leap-sdk
-
Updated
Sep 22, 2026 - Kotlin
Add this topic to your repo
To associate your repository with the lfm2 topic, visit your repo's landing page and select "manage topics."