LLM-ADE_tiny-v0.001 / README.md
WilliamGazeley's picture
Upload LlamaForCausalLM
da75eb2 verified
|
raw
history blame
662 Bytes
metadata
language:
  - en
license: mit
tags:
  - finance
pipeline_tag: text-generation
widget:
  - text: How do call options benefit the buyer?
    example_title: Domain Specific QA
  - text: >-
      Why might a trader choose to quickly exit a losing position, even if they
      still believe in the original trade idea?
    example_title: Not-Advice
inference:
  parameters:
    temperature: 0.3
    repetition_penalty: 10
    min_new_tokens: 30

AlphaBlind Tiny v0.01

A very early demonstration of enhancing an LLM with domain knowledge using IRAI's LLM-ADE framework.

Note that this model is not instruction tuned, and is very small - do not use this version of the model as is.