A small language model that simulates a QuietStar like behaviour in a simplified agentic way.
12 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
87768a4d56ab · 2.3GB
model
archllama
·
parameters3.96B
·
quantizationQ4_K_S
2.3GB
template
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
63B
params
{"num_ctx":8192,"num_predict":2048,"stop":["\u003c|im_end|\u003e","\u003c|im_start|\u003e"],"tempera
135B
Readme
ThoughtStream-4B-v0.1
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.
HF repo: trollek/ThoughtStream-4B-v0.1 Quants: mradermacher/ThoughtStream-4B-v0.1-GGUF