![](https://github.com/arboreal-ai.png)
arboreal-ai
/
llama-2-7b-chat
Llama-2-7b-Chat (GPTQ) with additional generation parameters
Run arboreal-ai/llama-2-7b-chat 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
|
[INST]Tell me about AI[/INST]
|
Prompt to send to Llama v2
|
system_prompt |
string
|
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
|
System prompt that helps guide system behavior
|
max_new_tokens |
integer
|
512
Min: 1 Max: 4096 |
Number of new tokens
|
temperature |
number
|
1
Max: 5 |
Randomness of outputs, 0 is deterministic, greater than 1 is random
|
top_p |
number
|
0.95
Min: 0.01 Max: 1 |
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
|
repetition_penalty |
number
|
1
Max: 5 |
Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it
|
exponential_decay_start |
integer
|
512
Max: 4096 |
Number of tokens to wait before starting exponential decay.
|
exponential_decay_factor |
number
|
1
Min: 1 Max: 10 |
Decay factor for LogitProcessor exponential decay.
|
skip_prompt |
boolean
|
True
|
Whether to skip the prompt to .generate() or not. Useful e.g. for chatbots.
|
random_seed |
integer
|
0
|
Random seed for reproducibility. Set to 0 for no random seed.
|
{
"type": "object",
"title": "Input",
"properties": {
"top_p": {
"type": "number",
"title": "Top P",
"default": 0.95,
"maximum": 1,
"minimum": 0.01,
"x-order": 4,
"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",
"default": "[INST]Tell me about AI[/INST]",
"x-order": 0,
"description": "Prompt to send to Llama v2"
},
"random_seed": {
"type": "integer",
"title": "Random Seed",
"default": 0,
"x-order": 9,
"description": "Random seed for reproducibility. Set to 0 for no random seed."
},
"skip_prompt": {
"type": "boolean",
"title": "Skip Prompt",
"default": true,
"x-order": 8,
"description": "Whether to skip the prompt to .generate() or not. Useful e.g. for chatbots."
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 1,
"maximum": 5,
"minimum": 0,
"x-order": 3,
"description": "Randomness of outputs, 0 is deterministic, greater than 1 is random"
},
"system_prompt": {
"type": "string",
"title": "System Prompt",
"default": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
"x-order": 1,
"description": "System prompt that helps guide system behavior"
},
"max_new_tokens": {
"type": "integer",
"title": "Max New Tokens",
"default": 512,
"maximum": 4096,
"minimum": 1,
"x-order": 2,
"description": "Number of new tokens"
},
"repetition_penalty": {
"type": "number",
"title": "Repetition Penalty",
"default": 1,
"maximum": 5,
"minimum": 0,
"x-order": 5,
"description": "Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it"
},
"exponential_decay_start": {
"type": "integer",
"title": "Exponential Decay Start",
"default": 512,
"maximum": 4096,
"minimum": 0,
"x-order": 6,
"description": "Number of tokens to wait before starting exponential decay."
},
"exponential_decay_factor": {
"type": "number",
"title": "Exponential Decay Factor",
"default": 1,
"maximum": 10,
"minimum": 1,
"x-order": 7,
"description": "Decay factor for LogitProcessor exponential decay."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output"
}