replicate-internal
/
llama-3-8b-instruct-fp16-triton
- Public
- 124 runs
Run replicate-internal/llama-3-8b-instruct-fp16-triton with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
|---|---|---|---|
| prompt |
string
|
Prompt to send to the model.
|
|
| system_prompt |
string
|
You are a helpful assistant
|
System prompt to send to the model. This is prepended to the prompt and helps guide system behavior.
|
| max_tokens |
integer
|
512
Min: 1 |
Maximum number of tokens to generate. A word is generally 2-3 tokens.
|
| min_tokens |
integer
|
Min: -1 |
Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
|
| temperature |
number
|
0.7
Max: 5 |
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
|
| top_p |
number
|
0.95
Max: 1 |
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens.
|
| top_k |
integer
|
0
Min: -1 |
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens.
|
| stop_sequences |
string
|
<|end_of_text|>,<|eot_id|>
|
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>'.
|
| length_penalty |
number
|
1
Max: 5 |
A parameter that controls how long the outputs are. If < 1, the model will tend to generate shorter outputs, and > 1 will tend to generate longer outputs.
|
| presence_penalty |
number
|
0
|
A parameter that penalizes repeated tokens regardless of the number of appearances. As the value increases, the model will be less likely to repeat tokens in the output.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed.
|
|
| prompt_template |
string
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
Template for formatting the prompt. Can be an arbitrary string, but must contain the substring `{prompt}`.
|
| log_performance_metrics |
boolean
|
False
|
None
|
| max_new_tokens |
integer
|
Min: 1 |
This parameter has been renamed to max_tokens. max_new_tokens only exists for backwards compatibility purposes. We recommend you use max_tokens instead. Both may not be specified.
|
| min_new_tokens |
integer
|
Min: -1 |
This parameter has been renamed to min_tokens. min_new_tokens only exists for backwards compatibility purposes. We recommend you use min_tokens instead. Both may not be specified.
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 10,
"description": "Random seed. Leave blank to randomize the seed."
},
"top_k": {
"type": "integer",
"title": "Top K",
"default": 0,
"minimum": -1,
"x-order": 6,
"description": "When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens."
},
"top_p": {
"type": "number",
"title": "Top P",
"default": 0.95,
"maximum": 1,
"minimum": 0,
"x-order": 5,
"description": "When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens."
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Prompt to send to the model."
},
"max_tokens": {
"type": "integer",
"title": "Max Tokens",
"default": 512,
"minimum": 1,
"x-order": 2,
"description": "Maximum number of tokens to generate. A word is generally 2-3 tokens."
},
"min_tokens": {
"type": "integer",
"title": "Min Tokens",
"minimum": -1,
"x-order": 3,
"description": "Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens."
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 0.7,
"maximum": 5,
"minimum": 0,
"x-order": 4,
"description": "Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value."
},
"system_prompt": {
"type": "string",
"title": "System Prompt",
"default": "You are a helpful assistant",
"x-order": 1,
"description": "System prompt to send to the model. This is prepended to the prompt and helps guide system behavior."
},
"length_penalty": {
"type": "number",
"title": "Length Penalty",
"default": 1,
"maximum": 5,
"minimum": 0,
"x-order": 8,
"description": "A parameter that controls how long the outputs are. If < 1, the model will tend to generate shorter outputs, and > 1 will tend to generate longer outputs."
},
"max_new_tokens": {
"type": "integer",
"title": "Max New Tokens",
"minimum": 1,
"x-order": 13,
"description": "This parameter has been renamed to max_tokens. max_new_tokens only exists for backwards compatibility purposes. We recommend you use max_tokens instead. Both may not be specified."
},
"min_new_tokens": {
"type": "integer",
"title": "Min New Tokens",
"minimum": -1,
"x-order": 14,
"description": "This parameter has been renamed to min_tokens. min_new_tokens only exists for backwards compatibility purposes. We recommend you use min_tokens instead. Both may not be specified."
},
"stop_sequences": {
"type": "string",
"title": "Stop Sequences",
"default": "<|end_of_text|>,<|eot_id|>",
"x-order": 7,
"description": "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>'."
},
"prompt_template": {
"type": "string",
"title": "Prompt Template",
"default": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>",
"x-order": 11,
"description": "Template for formatting the prompt. Can be an arbitrary string, but must contain the substring `{prompt}`."
},
"presence_penalty": {
"type": "number",
"title": "Presence Penalty",
"default": 0,
"x-order": 9,
"description": "A parameter that penalizes repeated tokens regardless of the number of appearances. As the value increases, the model will be less likely to repeat tokens in the output."
},
"log_performance_metrics": {
"type": "boolean",
"title": "Log Performance Metrics",
"default": false,
"x-order": 12
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "array",
"items": {
"type": "string"
},
"title": "Output",
"x-cog-array-type": "iterator",
"x-cog-array-display": "concatenate"
}