|
--- |
|
license: apache-2.0 |
|
--- |
|
## llama-2-7b-miniguanaco |
|
|
|
This is my first model, with LLama-2-7b model finetuned with miniguanaco datasets. |
|
|
|
This is a simple finetune based off a Google Colab notebook. Finetune instructions were from Labonne's first tutorial. |
|
|
|
To run it: |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import math |
|
|
|
model_path = "decruz07/llama-2-7b-miniguanaco" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True |
|
) |
|
print(model) |
|
prompt = input("please input prompt:") |
|
while len(prompt) > 0: |
|
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda") |
|
|
|
generation_output = model.generate( |
|
input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2 |
|
) |
|
print(tokenizer.decode(generation_output[0])) |
|
prompt = input("please input prompt:") |
|
|