0xsmw/workgpt 🔢📝 → 📝
About
Helps you with work
Example Output
Performance Metrics
2.24s
Prediction Time
309.99s
Total Time
Input Parameters
- n
- Number of output sequences to generate
- top_p
- When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
- prompt (required)
- Prompt to send to LLaMA.
- temperature
- Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
- total_tokens
- Maximum number of tokens for input + generation. A word is generally 2-3 tokens
- repetition_penalty
- 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
Version Details
- Version ID
9c622c147aef92f93d69508d1ce29cfac94829cc6b17e1c772a0a1bf2154ead0- Version Created
- April 14, 2023