Atome-FE / llama-node

Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model.

https://llama-node.vercel.app/

Atome-FE/llama-node Issues

What files are compatible?
Updated 2 months ago
Alternative?
Updated 4 months ago1
napi: not found on debian bullseye
Updated 5 months ago5
fatal runtime error: Rust cannot catch foreign exceptions
Updated 6 months ago5
GGUF support?
Updated 6 months ago
cannot use RWKV models
Updated 7 months ago16
Instructions for use with Electron
Updated 8 months ago
Can't run example on llama-2-13b-chat q4_0
Updated 8 months ago2
GPU version build not using GPU
Updated 8 months ago11
use with Next.js (webpack fails to load binary file)
Updated 9 months ago3
Time printings are gone
Updated 9 months ago
The requested module 'llama-node/dist/llm/llama-cpp.js' does not provide an export named 'LoadConfig'
Updated 9 months ago
Support for passing grammars
Updated 9 months ago
Discord Access
Closed 9 months ago1
Segmentation fault
Updated 10 months ago1
[Error: Failed to get embeddings] { code: 'GenericFailure' }
Updated 10 months ago
Code only using 4 CPU, when I have 16 CPU
Updated 10 months ago3
foreign exception error
Updated 10 months ago12
Llama2 quantized q5_1
Updated 10 months ago1
Unable to load latest GGML models using llama.cpp after latest quantisation changes
Closed a year ago3
中文乱码
Updated 10 months ago
Use custom tokenizer
Updated 10 months ago
Should bring details in error message
Updated 10 months ago
Unsupported file version 101 when loading rwkv
Updated 10 months ago
Issue to build GPU version
Closed a year ago1
Llama.cpp Typescript: Cannot find name 'LoadModel'
Closed a year ago
Support for the new k-quant methods in Llama.cpp
Updated a year ago
the software has no reaction with no errors
Updated a year ago
Can't run the example on MacOS M1 pro
Updated a year ago
Bumping from 0.1.5 to 0.1.6 resulting with `Error: invariant broken`
Updated a year ago
no kernel image is available for execution on the device
Updated a year ago2
llama-node/llama-cpp uses more memory than standalone llama.cpp with the same parameters
Updated a year ago3
Ggml v3 support in Llama.cpp
Closed a year ago4
Error: Missing field `nGpuLayers`
Updated a year ago6
Failed to convert napi value into rust type `bool`
Closed a year ago1
Error: Too many tokens predicted
Closed a year ago1
Segmentation fault local cuda build
Updated a year ago
[ERROR] cublas `TypeError: this.instance.inference is not a function`
Updated a year ago3
Embeddings.js file does not work correctly
Updated a year ago
langchain integration
Updated a year ago2
basic unified API for all backends
Updated a year ago3
app crashes when input is too long
Closed a year ago6
getting error after second run
Closed a year ago
TypeError: llm._modelType is not a function
Updated a year ago1
Illegal instruction (core dumped)
Updated a year ago4
req: support async/await
Updated a year ago8
Error: Failed to convert napi value Function into rust type `f64`
Updated a year ago5
is this supposed to have a gpu to run?
Closed a year ago2
[Error: Could not load model] { code: 'GenericFailure' }
Updated a year ago8
¿Update cross-compile.mts with aarch64 architecture?
Updated a year ago1