You're looking at a specific version of this model. Jump to the model overview.
ritabratamaiti /instructmix-llama-3b:a5631f28
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| instruction |
string
|
Describes the task the model should perform. Must be provided if format_prompt is True.
|
|
| input |
string
|
Optional context or input for the task. Used to generate a prompt if format_prompt is True.
|
|
| response_prefix |
string
|
Optional response prefix. It will be added to the beginning of the response and will help guide the response generation.
|
|
| temperature |
number
|
0.1
Min: 0.01 Max: 5 |
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic. (minimum: 0.01; maximum: 5)
|
| top_p |
number
|
0.75
Min: 0.01 Max: 1 |
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens (minimum: 0.01; maximum: 1)
|
| top_k |
integer
|
40
Min: 1 Max: 100 |
The number of highest probability vocabulary tokens to keep for top-k-filtering (minimum: 1; maximum: 100)
|
| num_beams |
integer
|
4
Min: 1 Max: 10 |
Number of beams for beam search (minimum: 1; maximum: 10)
|
| repetition_penalty |
number
|
1.1
Min: 0.01 Max: 5 |
Penalize repeated words. (minimum: 0.01; maximum: 5)
|
| max_new_tokens |
integer
|
128
Min: 1 Max: 512 |
Maximum number of new tokens to generate. A word is 2-3 tokens. (minimum: 1; maximum: 512)
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'title': 'Output', 'type': 'string'}