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 namePoolnoodle-LongNoodle
FamilyPoolnoodle
Model Base UUID9aad7c4e-85b7-472d-a362-7528054435c5
ParametersCirca 13 billion
OriginLlama 2
LicenseLLama 2 license and ScaiLabs Model License
Context Length131072
RoPE Scaling SupportedYes, dynamic
Tokenizerscaitoken-1
Embeddings modelscailar-1
Runtime compatibilityHF Transformers, FastChat

Model Versions

VersionVersion StringRelease dateUUID
0.1poolnoodle-0.1-longnoodle2023-12-22fa1c2c2f-65be-4937-a58d-9c874a74a993
0.2poolnoodle-0.2-longnoodle2023-10-134954b497-87f0-4c0e-b29a-fb27bfcda8d1
Back to top