fofr/llama2-prompter 🔢✓📝 → 📝

▶️ 515 runs 📅 Aug 2023 ⚙️ Cog 0.8.1
prompt-generation text-generation

About

Llama2 13b base model fine-tuned on text to image prompts

Example Output

Prompt:

"[PROMPT] a spooky ghost, in the style of"

Output

[PROMPT] a spooky ghost, in the style of realistic illustrations, fantasy art, cg, shiny, cobwebs, 32k uhd, dark gray and amber

Performance Metrics

3.81s Prediction Time
3.76s Total Time
All Input Parameters 
{
  "debug": false,
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "[PROMPT] a spooky ghost, in the style of",
  "temperature": 0.75,
  "max_new_tokens": 128,
  "min_new_tokens": 10,
  "stop_sequences": "[/PROMPT]"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
debug Type: booleanDefault: false
provide debugging output in logs
top_k Type: integerDefault: 50Range: 0 - ∞
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
top_p Type: numberDefault: 0.9Range: 0 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string
Prompt to send to the model.
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.
max_new_tokens Type: integerDefault: 128Range: 1 - ∞
Maximum number of tokens to generate. A word is generally 2-3 tokens
min_new_tokens Type: integerDefault: -1Range: -1 - ∞
Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
stop_sequences Type: string
A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.
replicate_weights Type: string
Path to fine-tuned weights produced by a Replicate fine-tune job.
Output Schema

Output

Type: array • Items Type: string

Example Execution Logs 
Your formatted prompt is:
[PROMPT] a spooky ghost, in the style of
Version Details
Version ID
818f7a50069e243f1fa6a7881e1710aea3aa3f0132f3f37e6dab69a4b59fcef0
Version Created
September 1, 2023
Run on Replicate →