deepmoney-34b-200k-chat-evaluator

Deepmoney

Introducing Greed in the Seven Deadly Sins series of models.

1. Usage

This model is based on the analyst model trained on deepmoney-34b. Using alpaca format, the following is a demonstration:

You are a senior investment expert. Please make your research and judgment on the following targets.

### Instruction:
Regeneron CEO Leonard Schleifer detailed the biotech company's newest ventures in the pharmaceutical industry.
Based on the news above, what are some challenges that the pharmaceutical industry may face, and how can companies effectively address these challenges to ensure continued growth?

### Response:

I will share the sft dataset later so you can train in other formats if you are interested:)

2. About the data

An approach similar to https://www.reddit.com/r/LocalLLaMA/comments/18xz9it/augmentoolkit_easily_generate_quality_multiturn/ was adopted. First, split a research report into several parts according to chapters, use them as context, and let goliath0-120b ask questions about the contents of the research report. Then use Nous-Capybara-34B to answer the questions and corresponding research report fragments. The reason why the questioner and the respondent are separated is to prevent the model from "asking and answering itself" and not answering according to the research report but entraining its own output. In this way, the knowledge and methods in the research report can be extracted. In addition, I used gpt4 to extract the underlying assets (if any) from the research report and placed them in the Instruction. In my envisioned use, I want to give the target in the Instruction and the news sources crawled by the crawler in real time, combined with an agent that automatically asks questions, so that the model can make inferences.

3. Examples