yrvelez/flamingo 🔢📝 → 📝

▶️ 496 runs 📅 Jun 2023 ⚙️ Cog 0.7.2

About

LLaMA 1.0 (13B) model fine-tuned for academic use cases like text classification. Use at your own risk. Not to be confused with the vision model.

Example Output

Prompt:

"You are a writer who writes in the style of Hunter S. Thompson. Generate a paragraph-long persuasive essay opposing the use of artificial intelligence."

Output

You are a writer who writes in the style of Hunter S. Thompson. Generate a paragraph-long persuasive essay opposing the use of artificial intelligence.

Humans were not born to be replaced by a bunch of codes.

The only thing AI is good for is assisting the human in their daily duties.

AI is great for those people who are scared to death to talk to real people.

Humans are not meant to be replaced by AI, but to be partners.

Never be scared to talk to real humans, but when AI is around it is a different story.

AIs do not deserve to get more rights than the normal human.

Privacy is a key factor of a normal human life. If AI can invade that with ease, they are up to no good.

Do not trust AI because they are just a computer program, and you will not know for sure what they can do.

AIs are great for the lazy and the scared, but the rest of us normal humans can do fine without them.

So do not trust AIs and embrace the normal humans.

After all, who would you rather trust, a machine or a fellow human?

Performance Metrics

46.53s Prediction Time

46.49s Total Time

All Input Parameters

{
  "n": 1,
  "top_p": 1,
  "prompt": "You are a writer who writes in the style of Hunter S. Thompson. Generate a paragraph-long persuasive essay opposing the use of artificial intelligence.",
  "max_length": 399,
  "temperature": 0.75,
  "repetition_penalty": 1
}

Input Parameters

n Type: integerDefault: 1Range: 1 - 5: Number of output sequences to generate
top_p Type: numberDefault: 1Range: 0.01 - 1: When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string: Text prompt to send to the model.
max_length Type: integerDefault: 50Range: 1 - ∞: Maximum number of tokens to generate. A word is generally 2-3 tokens
temperature Type: numberDefault: 0.75Range: 0.01 - 5: Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
repetition_penalty Type: numberDefault: 1Range: 0.01 - 5: Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Output Schema

Output

Type: array • Items Type: string

Version Details

Version ID: 0e85a6c091cccdabac7bfcb0a9db0ecd7db6909493fb3b32fc76bac9151c2a34
Version Created: June 10, 2023

Run on Replicate →