from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RootYuan/opt-350m-alpaca")
model = AutoModelForCausalLM.from_pretrained("RootYuan/opt-350m-alpaca")

usage:

instruction = "Classify the following into animals, plants, and minerals"
input = "Oak tree, copper ore, elephant"

prompts_no_input = f"### Instruction:\n{instruction}\n\n### Response:"
prompts_with_input = f"### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:"
prompts = prompts_no_input if input is None else prompts_with_input

inputs = tokenizer.encode(prompts, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=64)
ans = tokenizer.decode(outputs[0]).strip('</s>')[len(prompts):]
if input is None:
    print(f"Human: {instruction}")
else:
    print(f"Human: {instruction}\nInput: {input}")
print(f"Assistant: {ans}")

outputs:

Human: Classify the following into animals, plants, and minerals
Input: Oak tree, copper ore, elephant
Assistant: Oak tree: Plant
           Copper ore: Mineral
           Elephant: Animal

Other Examples:
Human: Say 'Hi'
Assistant: Hi! How can I help you today?

Human: Give me three helpful tips about health
Assistant: 1. Eat a balanced diet. 2. Get enough sleep. 3. Exercise regularly.

Human: Generate a list of ten items a person might need for a camping trip
Assistant: 1. Tent 2. Sleeping bag 3. Flashlight 4. Matches 5. First Aid Kit 6. Matches 7. Flashlight 8. Matches 9. Water Bottle 10. Matche

Human: Evaluate this sentence for spelling and grammar mistakes
Input: He finnished his meal and left the resturant
Assistant: He finished his meal and left the restaurant.

Human: Solve the following problem in python.
Input: Given variable a and variable b, return then sum of the a and b.
Assistant: sum = a + b
print(sum)

Human: Classify the following into animals, plants, and minerals
Input: Oak tree, copper ore, elephant
Assistant: Oak tree: Plant Copper ore: Mineral Elephant: Animal

Human: Do you know TikTok?
Assistant: Yes, TikTok is an online video platform that is popular with users around the world. It is a platform that allows users to create and share short videos, and it has over 1 billion users worldwide.

Human: Discuss the causes of the Great Depression
Assistant: The Great Depression was caused by a combination of factors, including a lack of economic growth, a decrease in consumer spending, and a decrease in the availability of credit. These factors combined to create a severe economic downturn that lasted for more than two decades.

Downloads last month
17
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.