ctransformers
lamp
ctransformers | lamp | |
---|---|---|
4 | 1 | |
1,718 | 25 | |
- | - | |
8.6 | 7.1 | |
4 months ago | 6 days ago | |
C | Scala | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ctransformers
-
Refact LLM: New 1.6B code model reaches 32% HumanEval and is SOTA for the size
Does ctransformer (https://github.com/marella/ctransformers#supported-models) support running refact?
I see that model type "gpt_refact" in https://huggingface.co/smallcloudai/Refact-1_6B-fim/blob/mai...
-
How do I utilize these quantized models being uploaded?
You can also use ctransformers with the ggml models if you want to use python rather than c++.
-
Langchain and self hosted LLaMA hosted API
For ggml https://github.com/marella/ctransformers/ and https://github.com/abetlen/llama-cpp-python has a decent server. https://github.com/go-skynet/LocalAI is very active too.
- Also reconnecting with Scala. Interested in LLMs
lamp
What are some alternatives?
llama-cpp-python - Python bindings for llama.cpp
ocaml-torch - OCaml bindings for PyTorch
LangChain_PDFChat_Oobabooga - oobaboga -text-generation-webui implementation of wafflecomposite - langchain-ask-pdf-local
TornadoVM - TornadoVM: A practical and efficient heterogeneous programming framework for managed languages
text-generation-inference - Large Language Model Text Generation Inference
scanet3 - Type-safe, high performance, distributed Neural networks in Scala
artificial-nose - Instructions, source code, and misc. resources needed for building a Tiny ML-powered artificial nose.
norse - Deep learning with spiking neural networks (SNNs) in PyTorch.
kendryte-standalone-sdk - Standalone SDK for kendryte K210
hyperlearn - 2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
ML-Workspace - 🛠All-in-one web-based IDE specialized for machine learning and data science.