Created
March 27, 2024 04:22
-
-
Save mrmaheshrajput/342ea15db1ab5cf5cfb59d32715b1995 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
!pip install sagemaker -q | |
from sagemaker.jumpstart.model import JumpStartModel | |
model_id, model_version, = ( | |
"huggingface-llm-falcon-7b-instruct-bf16", | |
"*", | |
) | |
my_model = JumpStartModel(model_id=model_id) | |
example_payloads = my_model.retrieve_all_examples() | |
predictor = my_model.deploy() | |
# This may not work | |
for payload in example_payloads: | |
response = predictor.predict(payload.body) | |
print("Input:\n", payload.body[payload.prompt_key]) | |
print("Output:\n", response[0]["generated_text"], "\n\n===============\n") | |
# Sample | |
prompt = "Tell me about Amazon SageMaker." | |
payload = { | |
"inputs": prompt, | |
"parameters": { | |
"do_sample": True, | |
"top_p": 0.9, | |
"temperature": 0.8, | |
"max_new_tokens": 1024, | |
"stop": ["<|endoftext|>", "</s>"], | |
}, | |
} | |
response = predictor.predict(payload) | |
print(response[0]["generated_text"]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment