Skip to main content

Poolnoodle-FixerNoodle

poolnoodle_fixernoodle_cropped.pngPoolnoodle-FixerNoodle is an LLM trained to route requests between LLMs and plugins. It's a model13 billion model, based on the original Poolnoodle model, which has its roots in the Vicuna 13B model.

The model has been trained to interact with several so called "plugins", which allow the model to use external resources.

 

Model Faceplate

Model name Poolnoodle-LongNoodleFixerNoodle
Family Poolnoodle
Model Base UUID 9aad7c4e-85b7-472d-a362-7528054435c58ca20c3e-7266-49f2-8a51-5ccec1289226
Parameters Circa 13 billion
Origin Llama 2Vicuna
License LLama 2 license and ScaiLabs Model License
Context Length 131072
RoPE Scaling Supported Yes, dynamicNo
Tokenizer scaitoken-1Llama tokenizer
Embeddings model scailar-1Llama embeddings
Runtime compatibility HF Transformers, FastChatFastChat, ScaiBlossom

Model Versions

Version Version String Release date UUID
0.1 poolnoodle-0.1-longnoodlefixernoodle 2023-12-222024-02-04 fa1c2c2f-65be-4937-a58d-9c874a74a993
0.2poolnoodle-0.2-longnoodle2023-10-134954b497-87f0-4c0e-b29a-fb27bfcda8d17ea3dd93-93d1-44b3-9e38-520b7416a475