Addestra il tuo Mini Language Model!
-
Updated
Oct 1, 2025 - Jupyter Notebook
#
smollm2
Here are 22 public repositories matching this topic...
A lightweight voice companion, optimized for macOS.
macos translation tts macosx sst mlx voice-assistant edge-ai llm coqui-tts llms openai-whisper llm-inference small-language-models smollm2
-
Updated
Oct 28, 2025 - Python
A set of reference implementations for various ML related tasks
opencv ai mcp scikit-learn ml pytorch langchain langchain-python segment-anything llama2 langgraph llama3 smollm2 browser-use smolagents
-
Updated
Aug 31, 2025 - Jupyter Notebook
Real-Time VLM Visual Analysis Web App
-
Updated
Sep 16, 2025 - Python
Kurtis is a fine-tuning, inference and evaluation tool built for SLMs (Small Language Models), such as Huggingface's SmolLM2.
machine-learning ai ml transformers question-answering mental-health mental-health-awareness slms huggingface-transformers llm llm-training llm-inference small-language-models huggingface-peft question-answering-model smollm smollm2 huggingface-smollm2
-
Updated
Mar 17, 2026 - Python
A fine-tuned version of SmolLM2-360M-Instruct-bnb-4bit specialized for parsing unstructured calendar event requests into structured JSON data.
json transformers llama fine-tuning calender-event huggingface huggingface-transformers huggingface-models text-to-json generative-ai instruction-tuning llamacpp finetuning-llms ollama finetuning-large-language-models small-language-models smollm smollm2 text2json text-2-json
-
Updated
Jun 21, 2025 - Python
Active-inference Training with Learned Adaptive Stigmergy — Pure Rust AGI framework, 21 crates, 565 tests, 28 MCP tools, BF16 GPU inference (15.4 tok/s OLMo-3-7B on A100), OpenAI-compatible API, ZK proofs. Zero external dependencies.
training rust open-source machine-learning reinforcement-learning gpu mcp cuda agi causal-inference stigmergy astra pheromone zero-dependencies active-inference zk-proofs llm smollm2 openai-compatible graphpalace
-
Updated
Apr 20, 2026 - Rust
NMOS (Neural Memory OS) is a predictive partial execution engine enabling 70B-level reasoning on 4GB VRAM. It uses the “Zero-Lag” hypothesis, leveraging typing latency as a compute window to mask memory limits via async layer prefetching and speculative decoding.
python machine cuda pytorch memory-management hnsw edge-ai llm generative-ai local-llm llm-inference speculative-decoding smollm2 vram-optimization anticipatory-inference layer-offloading prefeching 70b-model
-
Updated
Apr 6, 2026 - Python
Systematically train and benchmark Mistral, Qwen2.5, and SmolLM2 on essay grading across 39 experiments through data analysis and engineering, structured preprocessing, instruction tuning, postprocessing, and leakage aware evaluation for robust score and rationale generation
modeling evaluation transformers data-engineering data-analysis lora preprocessing postprocessing automatic-essay-scoring instruction-tuning supervised-finetuning flash-attention-2 mistral-7b unsloth qwen2-5 smollm2
-
Updated
Aug 14, 2025 - Jupyter Notebook
Run SmolLM2 in a web browser with transformers.js
-
Updated
Dec 1, 2024 - TypeScript
he point is not the model — the point is the pattern. Fork it, swap SmolLM2 for any model you want, and you have your own private LLM API running for free.
-
Updated
Apr 9, 2026 - Python
Build a system that analyzes resumes using NLP techniques, including preprocessing, skill extraction, and similarity scoring.
python extractor evaluation preprocessor similarity spacy transformer nltk accuracy recall tf-idf recommendation precision bert f1-score streamlit sentence-transformers resume-analyzer smollm2 skill-matching
-
Updated
Jul 9, 2025 - Jupyter Notebook
A lightweight, locally hosted LLM pipeline that extracts and normalizes unstructured student assignment text into a strict JSON schema using a fine-tuned SmolLM2-360M model served via Ollama.
-
Updated
Apr 19, 2026 - Jupyter Notebook
ARIA is an AI-powered voice assistant that provides intelligent, web-enhanced answers to user queries. Built using a lightweight HuggingFace model, it integrates real-time web search and responds in a professional tone.
-
Updated
Apr 28, 2025 - HTML
Adaptive tiny-model layer between LLMs and their tools — observes MCP traffic, trains per-tool LoRA compressors, synthesizes new tools from patterns.
agent mcp lora peft tool-use llm prompt-compression smollm2 model-context-protocol claude-code token-optimization
-
Updated
Apr 24, 2026 - Python
Minimal Go implementation for inference Hugging Face SmolLM2 Instruct models.
-
Updated
Apr 27, 2026 - Go
A comprehensive toolkit for fine-tuning Large Language Models (LLMs) using cutting-edge techniques like LoRA, QLoRA, and Unsloth. Includes notebooks and scripts for customizing models such as SmolLM2, Llama-3.2, and Embedding Gemma for tasks like tool calling, reasoning, and embeddings. Perfect for researchers and developers looking to adapt LLMs
-
Updated
Jan 15, 2026 - Jupyter Notebook
Free, open-source, privacy-focused, customizable AI chatbot.
-
Updated
Dec 13, 2025 - TypeScript
Improve this page
Add a description, image, and links to the smollm2 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the smollm2 topic, visit your repo's landing page and select "manage topics."