ByFinTech's picture
Update README.md
92de73e
metadata
license: mit

library_name: peft

FinGPT_v3.3 for sentiment analysis

Model info

  • Base model: Llama2-13B
  • Training method: Instruction Fine-tuning + LoRA
  • Task: Sentiment Analysis

Packages

!pip install transformers==4.32.0 peft==0.5.0
!pip install sentencepiece
!pip install accelerate
!pip install torch
!pip install peft
!pip install datasets
!pip install bitsandbytes

Inference: Try the model in Google Colab

from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizerFast
from peft import PeftModel  # 0.5.0

# Load Models
base_model = "NousResearch/Llama-2-13b-hf" 
peft_model = "FinGPT/fingpt-sentiment_llama2-13b_lora"
tokenizer = LlamaTokenizerFast.from_pretrained(base_model, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
model = LlamaForCausalLM.from_pretrained(base_model, trust_remote_code=True, device_map = "cuda:0", load_in_8bit = True,)
model = PeftModel.from_pretrained(model, peft_model)
model = model.eval()

# Make prompts
prompt = [
'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
Input: FINANCING OF ASPOCOMP 'S GROWTH Aspocomp is aggressively pursuing its growth strategy by increasingly focusing on technologically more demanding HDI printed circuit boards PCBs .
Answer: ''',
'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
Input: According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .
Answer: ''',
'''Instruction: What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}
Input: A tinyurl link takes users to a scamming site promising that users can earn thousands of dollars by becoming a Google ( NASDAQ : GOOG ) Cash advertiser .
Answer: ''',
]

# Generate results
tokens = tokenizer(prompt, return_tensors='pt', padding=True, max_length=512)
res = model.generate(**tokens, max_length=512)
res_sentences = [tokenizer.decode(i) for i in res]
out_text = [o.split("Answer: ")[1] for o in res_sentences]

# show results
for sentiment in out_text:
    print(sentiment)

# Output:    
# positive
# neutral
# negative

Training Script: Our Code

#llama2-13b-nr
deepspeed -i "localhost:2" train_lora.py \
--run_name sentiment-llama2-13b-20epoch-64batch \
--base_model llama2-13b-nr \
--dataset sentiment-train \
--max_length 512 \
--batch_size 64 \
--learning_rate 1e-4 \
--num_epochs 20 \
--from_remote True \
>train.log 2>&1 &

Training Data:

  • PEFT 0.5.0