slm
chatbot
Chatbot继续沿着LLM前进,近期更新小参数量SLM的和训练脚本,支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。
- 3.6k
- Python
- 14 mo ago
nobodywho
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
- 1.7k
- Rust
- EUPL-1.2
- 7 h ago
kapitsa
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
- 830
- C++
- Apache-2.0
- 28 min ago
slmsuite
Python package for high-performance spatial light modulator (SLM) control and holography. Supports features from aberration-corrected 3D point clouds to automated Fourier-domain calibrations.
- 202
- Python
- MIT
- 23 h ago
Llama-3.2-3B-F1-Reasoning-Instruct
Text generation model, used with transformers.
- 48
- 11
- llama3.2
- 20 mo ago
AFMTrainer
A comprehensive GUI wrapper application for Apple's Foundation Models Adapter Training Toolkit, providing an intuitive interface for training LoRA adapters for Apple's on-device foundation models.
- 19
- Python
- 5 mo ago
Llama-3.2-3B-F1-Reasoning-Instruct-GGUF
Text generation model, used with transformers.
Gated access
- 14
- 0
- llama3.2
- 11 mo ago
SLM Bistro
Run & Train Small LMs for Free w/ GGUF, PEFT & more!
Runs in the browser on Hugging Face
- 10
- apache-2.0
- 3 wk ago
RayCodes_Noema-2b
Qwen3.5 Just Got a Tiny Coding AI That Beats Models 3x Its Size! (Noema 2B Review) - Fast offline local terminal command generator powered by Noema-2B GGUF via Ollama.
- 3
- Python
- 2 mo ago
Marcella-66M-SLM
A 66M parameter decoder-only transformer language model implemented from scratch in PyTorch. Features a custom SentencePiece tokenizer, RoPE positional embeddings, SwiGLU feed-forward network, per-layer KV cache for efficient autoregressive inference, and a Svelte-based streaming chat interface.
- 2
- Python
- MIT
- 6 mo ago
cli
Terminal CLI for ZeroGPU — an ultra-fast, compute-efficient inference provider for apps and agents. Purpose-built small and nano models on an edge network, with zero GPU infrastructure, serverless, and auto-scaling built in.
- 1
- TypeScript
- MIT
- 3 wk ago
selectia
Selectia - A family of System One-style models fine-tuned from LFM 2.5, designed for one-pass typed decisions with calibrated probabilities. Decision API (Choice, Noul, Score) powered by open LLMs.
- 1
- Python
- 8 wk ago
Build_A_Small_Language_Model
A detail guide to build, train, fine-tune and deploye SLM. This repo contains code, examples and blog on building a small language model from scratch.
- 0
- Jupyter Notebook
- GPL-3.0
- 7 wk ago
SQUiD_neurosymbolic
Unofficial implementation of the "SQUiD: Synthesizing Relational Databases from Unstructured Text" paper.
- 0
- Python
- Apache-2.0
- 12 mo ago
audit-sem-krnl
Automated conformance audit systems for criticals infrastructures, built on **Semantic Kernel 1.74** and **C# / .NET 9**.
- 0
- C#
- 5 mo ago





