from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("./capital_llm_model")
model = AutoModelForCausalLM.from_pretrained("./capital_llm_model")

prompt = "Question: what is the capital of Kerala? Answer:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=30, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Prompt format

Question: <your question>? Answer:

nishal21/geo-capital-llm

geo-capital-llm

Training data

Usage

Prompt format

nishal21/
geo-capital-llm