A small language model that simulates a QuietStar like behaviour in a simplified agentic way.

Updated 1 year ago

1 year ago

1b7145223393 · 3.3GB ·

archllama

parameters3.96B

quantizationQ6_K

3.3GB

<|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant

63B

{ "num_ctx": 8192, "num_predict": 2048, "stop": [ "<|im_end|>", "<|im_st

135B

Readme

This model is based on h2oai/h2o-danube3-4b-base and fine-tuned using LoRA+ and BAdam with LLama-Factory. It uses the ChatML template, without a system message, and was trained on the ThoughtfulAssistant-v01 dataset.

The idea is to abstract the thoughts away or into a thought bubble when chatting.