This model is a fine-tuned Mistral-7B chatbot for predicting the price of bitcoin based on technical market trends. The main model can be found in stem-agent-1, which leverages https://brev.dev/ cloud GPUs and guide for fine-tuning a mistral model. The notebook requires 1x A10G 24GB for training, which takes around 10 minutes and costs a few dollars.

The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.

For full details of this model please read our paper and release blog post.

Model Architecture Mistral-7B-v0.1 is a transformer model, with the following architecture choices:

Grouped-Query Attention Sliding-Window Attention Byte-fallback BPE tokenizer