LLM-ADE_tiny-v0.001 / README.md
WilliamGazeley's picture
Upload tokenizer
ad8f797 verified
|
raw
history blame
1.1 kB
---
language:
- en
license: mit
tags:
- finance
pipeline_tag: text-generation
widget:
- example_title: Easy
text: '<|user|>
How do call options benefit the buyer?
<|assistant|>
'
- example_title: Medium
text: '<|user|>
Why might a trader choose to quickly exit a losing position, even if they still
believe in the original trade idea?
<|assistant|>
'
- example_title: Hard
text: '<|user|>
In the context of Harry Markowitz''s Portfolio Selection theory, what does an
''efficient'' portfolio refer to?
<|assistant|>
'
inference:
parameters:
temperature: 0.2
min_new_tokens: 20
max_new_tokens: 250
---
# AlphaBlind Tiny v0.001
Our Proof-of-Concept (POC) for the LLM-ADE framework (https://arxiv.org/abs/2404.13028). A very early, initial version of TinyLlama processing and ingesting llm-ade-fin_data-subset-earnings-10k and other financial data with the LLM-ADE framework.
Note: This model has not been thoroughly tested, and is very small - it can run on a Macbook Pro. Please do not use this version of the model as is.