llama2-13b-zsee-lora

This LoRA model was fine-tuned using the zeolite synthesis dataset ZSEE.

Usage:

import torch
from transformers import (
    AutoConfig,
    AutoTokenizer,
    AutoModelForCausalLM,
    GenerationConfig
)
from peft import PeftModel
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_path = 'meta-llama/Llama-2-13b-chat-hf'
lora_path = 'zimyu/llama2-13b-zsee-lora'

config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    config=config,
    device_map="auto",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(
    model,
    lora_path,
)
model.eval()

system_prompt = "<<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
sintruct = "{\"instruction\": \"You are an expert in event argument extraction. Please extract event arguments and their roles from the input that conform to the schema definition, which already includes event trigger words. If an argument does not exist, return NAN or an empty dictionary. Please respond in the format of a JSON string.\", \"schema\": [{\"event_type\": \"Add\", \"trigger\": [\"added\"], \"arguments\": [\"container\", \"material\", \"temperature\"]}, {\"event_type\": \"Stir\", \"trigger\": [\"stirred\"], \"arguments\": [\"sample\", \"revolution\", \"temperature\", \"duration\"]}], \"input\": \"Subsequently , the pre-prepared silicalite-1 seed was added to the above mixture and stirred for another 1 h , and the quantity of seed equals to 7.0 wt% of the total SiO2 in the starting gel .\"}"
sintruct = '[INST] ' + system_prompt + sintruct + ' [/INST]'

input_ids = tokenizer.encode(sintruct, return_tensors="pt").to(device)
input_length = input_ids.size(1)
generation_output = model.generate(input_ids=input_ids, generation_config=GenerationConfig(max_length=512, max_new_tokens=256, return_dict_in_generate=True))
generation_output = generation_output.sequences[0]
generation_output = generation_output[input_length:]
output = tokenizer.decode(generation_output, skip_special_tokens=True)

print(output)

Output:

{"Add": [{"container": "NAN", "material": ["above mixture", "pre-prepared silicalite-1 seed"], "temperature": "NAN"}], "Stir": [{"sample": "NAN", "revolution": "NAN", "temperature": "NAN", "duration": "1 h"}]}