FinGPT_v3.3

Model info

Base model: Llama2-13B
Training method: Instruction Fine-tuning + LoRA + 8bit
Task: Sentiment Analysis

Try the model

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 = "oliverwang15/FinGPT_v33_Llama2_13B_Sentiment_Instruction_LoRA_FT_8bit"
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 procedure

The following bitsandbytes quantization config was used during training:

quant_method: bitsandbytes
load_in_8bit: True
load_in_4bit: False
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

Framework versions

PEFT 0.5.0