Python bindings for the Transformer models implemented in C/C++ using GGML library.
-
Updated
Jan 28, 2024 - C
#
Transformers
Transformers provides thousands of pretrained models to perform tasks on text, vision, and audio. Developed by Hugging Face, it simplifies downloading, training, and fine-tuning state-of-the-art architectures including BERT, GPT, Llama, and Whisper across PyTorch, TensorFlow, and JAX backends.
Here are 33 public repositories matching this topic...
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
transformers pytorch speech-recognition speech-to-text transcription asr speaker-diarization on-device chinese-dialects llama-cpp real-time-asr gguf funasr audio-language-model multilingual-asr fun-asr whisper-alternative 31-languages llm-asr fun-asr-nano
-
Updated
Sep 10, 2026 - C
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
android web transformers pytorch speech-recognition chinese lora whisper asr huggingface ctranslate2
-
Updated
May 8, 2026 - C
Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.
embedded optimization esp32 transformers embedded-systems transformer kv embedded-c edge-ai ondeviceai ondevicemachinelearning quantilization esp32s3 esp32-s3 llm llm-inference edge-ai-models edge-ai-engineering ondevice-ai
-
Updated
Jul 30, 2026 - C
hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM, and VRAM into a single intelligent memory hierarchy, enabling inference of models like GPT-OSS 120B, GLM, DeepSeek, Qwen, and more on consumer hardware
open-source cross-platform transformers artificial-intelligence high-performance-computing memory-management glm systems-programming inference-engine c17 mixture-of-experts ai-inference large-language-models llm qwen deepseek sparse-moe llm-runtime gpt-oss
-
Updated
Jul 31, 2026 - C
a from-scratch, pure-C deep learning library for CPU-only training, emphasizing high performance and no external ML dependencies.
c deep-neural-networks deep-learning ml transformers pytorch neural-networks slm scratch-implementation matmul ggml
-
Updated
Sep 30, 2026 - C
Arianna Method Programming Language
programming-language technology transformers lora attention-mechanism gguf notorch arianna-method posttransformer janus-architecture
-
Updated
Oct 8, 2026 - C
Implementation of the core Transformer architecture in pure C
-
Updated
Sep 8, 2024 - C
A minimal library to run transformer neural networks on CPU.
-
Updated
Jun 24, 2023 - C
[NeurIPS'25] Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
-
Updated
May 11, 2026 - C
Index of eight pieces of modern AI rebuilt from the papers, each with a correctness harness, measured benchmarks and a write-up.
machine-learning research reinforcement-learning deep-learning reproducible-research transformers pytorch from-scratch optimal-transport diffusion-models rlhf flash-attention
-
Updated
Oct 10, 2026 - C
A lightweight C Transformer engine built for bare-metal CPU speed on Apple Silicon.
-
Updated
Sep 28, 2026 - C
C++ Implementation of Meta's LLaMA v2 Engine. Credited to ggerganov/llama.cpp
-
Updated
Oct 11, 2023 - C
A zero-dependency tensor and matrix library in pure C, built from scratch as the foundation for implementing Transformers without external ML frameworks.
-
Updated
Jul 1, 2026 - C
Pure C implementation of Multi-Head Attention from Attention Is All You Need, combining parallel attention heads with output projection—the core building block of modern Transformers and LLMs.
-
Updated
Jul 1, 2026 - C
Pure C training framework featuring a modular Trainer, DataLoader, SGD/Adam optimizers, learning-rate scheduling, callbacks, evaluation metrics, checkpointing, and end-to-end model training built from scratch.
c machine-learning deep-learning transformers optimizer sgd neural-networks dataloader gradient-descent pure-c callbacks adam checkpointing machine-learning-framework training-framework
-
Updated
Jul 20, 2026 - C
Pure C implementation of the Transformer Encoder Layer from Attention Is All You Need, composing Multi-Head Attention, residual connections, Layer Normalization, and Feed-Forward Networks into the first complete Transformer block.
c deep-learning transformers layer-normalization attention-is-all-you-need multi-head-attention feed-forward-neural-networks transformer-encoder encoder-layer
-
Updated
Jul 9, 2026 - C
Clean from-scratch math core for shannon-prime-lattice: KSTE encoder, Friedman sieve, ARM (HRR in CRT cyclotomic ring), CRT NTT primitives, Position-as-Arithmetic.
machine-learning ai machine-learning-algorithms transformers attention-mechanism attention-is-all-you-need transformer-encoder transformer-architecture transformer-models kvcache kvcache-optimization kvcache-compression
-
Updated
Sep 12, 2026 - C
Neural Network C is an advanced neural network implementation in pure C, optimized for high performance on CPUs and NVIDIA GPUs.
machine-learning encryption deep-learning neural-network openmp mpi parallel-computing cuda transformers artificial-intelligence high-performance-computing convolutional-neural-networks gpu-computing quantization bayesian-optimization multi-gpu c-programming real-time-monitoring secure-computing tensor-cores
-
Updated
Mar 29, 2025 - C
Pure C multi-class classifier with Softmax, Cross-Entropy Loss, and manual backpropagation—demonstrating the output layer used in modern language models.
-
Updated
Jul 1, 2026 - C
Created by huggingface
- Followers
- 198 followers
- Repository
- huggingface/transformer
- Website
- github.com/topics/transformers
