Search results

node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

• llama
• llama-cpp
• llama.cpp
• bindings
• ai
• cmake
• cmake-js
• prebuilt-binaries
• llm
• gguf
• metal
• cuda
• vulkan
• grammar
• View more

giladgd

• 3.3.0 • 18 hours ago • 14 dependents • MITpublished version 3.3.0, 18 hours ago14 dependents licensed under $MIT

llama.rn

React Native binding of llama.cpp

• react-native
• ios
• android
• large language model
• LLM
• Local LLM
• llama.cpp
• llama
• llama-2

jhen0409

• 0.4.3 • 12 days ago • 1 dependents • MITpublished version 0.4.3, 12 days ago1 dependents licensed under $MIT

hyllama

llama.cpp gguf file parser for javascript

• llama
• llama.cpp
• llama-cpp
• llamacpp
• llm
• gguf
• parser
• machine learning
• ml

platypii

• 0.2.2 • 7 months ago • 1 dependents • MITpublished version 0.2.2, 7 months ago1 dependents licensed under $MIT

cui-llama.rn

Fork of llama.rn for ChatterUI

• react-native
• ios
• android
• large language model
• LLM
• Local LLM
• llama.cpp
• llama
• llama-2

vali98

• 1.3.0 • 16 days ago • 0 dependents • MITpublished version 1.3.0, 16 days ago0 dependents licensed under $MIT

inference-server

Libraries and server to build AI applications. Adapters to various native bindings allowing local inference. Integrate it with your application, or use as a microservice.

• local ai
• inference server
• model pool
• gpt4all
• node-llama-cpp
• transformers.js
• llama.cpp
• chatbot
• bot
• llm
• ai
• nlp
• openai api

limez

• 1.0.0-beta.26 • 3 days ago • 0 dependents • MITpublished version 1.0.0-beta.26, 3 days ago0 dependents licensed under $MIT

@pocketpalai/llama.rn

React Native binding of llama.cpp

• react-native
• ios
• android
• large language model
• LLM
• Local LLM
• llama.cpp
• llama
• llama-2

aghorbani

• 0.3.12 • a month ago • 0 dependents • MITpublished version 0.3.12, a month ago0 dependents licensed under $MIT

@isdk/ai-tool-llm-llamacpp

llama.cpp LLM Provider

• ai
• ai-tool
• tool
• llm
• llamacpp
• llama.cpp

isdk

• 0.3.14 • 2 months ago • 1 dependentspublished version 0.3.14, 2 months ago1 dependents

@isdk/ai-tool-llm-llamacpp-pro

llama.cpp LLM Provider

• ai
• ai-tool
• tool
• llm
• llamacpp
• llama.cpp

isdk

• 0.1.15 • 2 months ago • 0 dependentspublished version 0.1.15, 2 months ago0 dependents

@aghorbani/llama.rn

React Native binding of llama.cpp

• react-native
• ios
• android
• large language model
• LLM
• Local LLM
• llama.cpp
• llama
• llama-2

aghorbani

• 0.3.12 • a month ago • 0 dependents • MITpublished version 0.3.12, a month ago0 dependents licensed under $MIT

quiad

Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level

• similique
• id
• llama.cpp
• bindings
• ai
• sequi
• blanditiis
• error
• llm
• laboriosam
• metal
• cuda
• grammar
• json-grammar
• View more

reinholdmacejkovic

• 1.3.1 • 8 months ago • 0 dependents • MITpublished version 1.3.1, 8 months ago0 dependents licensed under $MIT

@isdk/ai-tool-llm-openai

llama.cpp LLM Provider - OpenAI Compatible

• ai
• ai-tool
• tool
• llm
• llamacpp
• llama.cpp

isdk

• 0.1.3 • 2 months ago • 2 dependentspublished version 0.1.3, 2 months ago2 dependents

custom-koya-node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level

• llama
• llama-cpp
• llama.cpp
• bindings
• ai
• cmake
• cmake-js
• prebuilt-binaries
• llm
• gguf
• metal
• cuda
• grammar
• json-grammar
• View more

shakeebaftab-koya

• 0.1.0 • 4 months ago • 0 dependents • MITpublished version 0.1.0, 4 months ago0 dependents licensed under $MIT

llama.cpp-ts

Node.js bindings for LlamaCPP, a C++ library for running language models.

• node
• language-model
• c++
• cpp
• node-addon-api
• cmake
• cmake-js
• llama
• llama.cpp
• 3.1

michal.jarnot

• 1.2.0 • 2 months ago • 0 dependentspublished version 1.2.0, 2 months ago0 dependents

llama.native.js

use `npm i --save llama.native.js` to run lama.cpp models on your local machine. features a socket.io server and client that can do inference with the host of the model.

• llm
• wrapper
• huggingface
• javascript
• llama.cpp
• socket.io
• dalai
• quantized
• cpu
• text
• generation

daveinchy

• 1.1.0 • a year ago • 0 dependents • IDGASHITpublished version 1.1.0, a year ago0 dependents licensed under $IDGASHIT

grammar-builder

A simple grammar builder compatible with GBNF (llama.cpp)

• grammar
• llama.cpp
• GBNF
• constrained generation
• LLM

fimbulvntr

• 0.0.5 • 7 months ago • 0 dependents • MITpublished version 0.0.5, 7 months ago0 dependents licensed under $MIT

llama-ggml.js

serve websocket GGML 4/5bit Quantized LLM's based on Meta's LLaMa model with llama.ccp

• llm
• wrapper
• huggingface
• javascript
• llama.cpp
• socket.io
• dalai
• quantized
• cpu
• text
• generation

daveinchy

• 0.1.0 • 2 years ago • 0 dependents • ISCpublished version 0.1.0, 2 years ago0 dependents licensed under $ISC