marella/ctransformers
Python bindings for the Transformer models implemented in C/C++ using GGML library.
Provides CPU-optimized inference for quantized transformer models (GGML/GGUF formats) with streaming output and partial GPU offloading via CUDA/Metal/ROCm. Integrates seamlessly with Hugging Face Transformers pipelines and LangChain, supporting models like LLaMA, Falcon, and MPT with configurable layer-wise GPU acceleration and sampling parameters.
1,882 stars. No commits in the last 6 months.
Stars
1,882
Forks
143
Language
C
License
MIT
Category
Last pushed
Jan 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/marella/ctransformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/locoformer
LocoFormer - Generalist Locomotion via Long-Context Adaptation