01-ai/Yi-34B-200K cover image

01-ai/Yi-34B-200K

The Yi series models are large language models developed by 01.AI. They include Yi-6B and Yi-34B, which have 6 billion and 34 billion parameters respectively. There are also versions of these models with 200K context lengths. The models can be used for various NLP tasks such as text classification, sentiment analysis, question answering, etc. The models are available for academic research and free commercial usage with permission.

The Yi series models are large language models developed by 01.AI. They include Yi-6B and Yi-34B, which have 6 billion and 34 billion parameters respectively. There are also versions of these models with 200K context lengths. The models can be used for various NLP tasks such as text classification, sentiment analysis, question answering, etc. The models are available for academic research and free commercial usage with permission.

Public
$0.60/Mtoken
ProjectLicense

HTTP/cURL API

 

Input fields

inputstring

text to generate from


max_new_tokensinteger

maximum length of the newly generated generated text

Default value: 2048

Range: 1 ≤ max_new_tokens ≤ 100000


temperaturenumber

temperature to use for sampling. 0 means the output is deterministic. Values greater than 1 encourage more diversity

Default value: 0.7

Range: 0 ≤ temperature ≤ 100


top_pnumber

Sample from the set of tokens with highest probability such that sum of probabilies is higher than p. Lower values focus on the most probable tokens.Higher values sample more low-probability tokens

Default value: 0.9

Range: 0 < top_p ≤ 1


top_kinteger

Sample from the best k (number of) tokens. 0 means off

Default value: 0

Range: 0 ≤ top_k < 100000


repetition_penaltynumber

repetition penalty. Value of 1 means no penalty, values greater than 1 discourage repetition, smaller than 1 encourage repetition.

Default value: 1

Range: 0.01 ≤ repetition_penalty ≤ 5


stoparray

Up to 4 strings that will terminate generation immediately


num_responsesinteger

Number of output sequences to return. Incompatible with streaming

Default value: 1

Range: 1 ≤ num_responses ≤ 2


presence_penaltynumber

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Default value: 0

Range: -2 ≤ presence_penalty ≤ 2


frequency_penaltynumber

Positive values penalize new tokens based on how many times they appear in the text so far, increasing the model's likelihood to talk about new topics.

Default value: 0

Range: -2 ≤ frequency_penalty ≤ 2


webhookfile

The webhook to call when inference is done, by default you will get the output in the response of your inference request


streamboolean

Whether to stream tokens, by default it will be false, currently only supported for Llama 2 text generation models, token by token updates will be sent over SSE

Default value: false

Input Schema

Output Schema


© 2023 Deep Infra. All rights reserved.

Discord Logo