meta-llama/Llama-2-70b-chat-hf cover image
featured

meta-llama/Llama-2-70b-chat-hf

LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.

LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.

Public
$0.70/$0.95 in/out Mtoken
PaperLicense
meta-llama/Llama-2-70b-chat-hf cover image

llama 70b

 

0.00s

Tweak the overall style and tone of the conversation by giving some 'master' instructions. (Default: Be a helpful assistant)

maximum length of the newly generated generated text (Default: 2048, 1 ≤ max_new_tokens ≤ 100000)

Temperature

temperature to use for sampling. 0 means the output is deterministic. Values greater than 1 encourage more diversity (Default: 0.7, 0 ≤ temperature ≤ 1)

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: 0.9, 0 < top_p ≤ 1)

Sample from the best k (number of) tokens. 0 means off (Default: 0, 0 ≤ top_k < 100000)

Up to 4 strings that will terminate generation immediately. Please separate items by comma

 


© 2023 Deep Infra. All rights reserved.

Discord Logo