llama-2-7b-miniguanaco

BrokenSoul/llama-2-7b-miniguanaco

This is a test model finetuned for learning.

How to use

from transformers import (
    AutoTokenizer,
    pipeline
)

model_name = "BrokenSoul/llama-2-7b-miniguanaco"

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"

prompt = "What is a large language model?"
pipe = pipeline(task="text-generation", model=model_name, tokenizer=tokenizer, max_length=200)
result = pipe(f"<s>[INST] {prompt} [/INST]")
print(result[0]['generated_text'])

Training data

mlabonne/guanaco-llama2-1k dataset.

Training procedure

It was trained following the maximelabonne's guide. all credits for him.

---

license: apache-2.0 language:

• en pipeline_tag: text-generation

---