Update README.md

README.md

@@ -1,3 +1,83 @@
 ---
 license: mit
 ---
+
+# FinGPT sentiment analysis task
+
+## Model info
+- Base model:  InternLM-20B
+- Training method:  Instruction Fine-tuning + LoRA
+- Task:  Sentiment Analysis
+
+## Packages
+``` python
+!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
+``` python
+from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizerFast
+from peft import PeftModel  # 0.5.0
+
+# Load Models
+base_model = "internlm/internlm-20b" 
+peft_model = "FinGPT/fingpt-sentiment_internlm-20b_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](https://github.com/AI4Finance-Foundation/FinGPT/tree/master/fingpt/FinGPT_Benchmark)
+```
+#internlm-20b
+deepspeed -i "localhost:2" train_lora.py 
+--run_name sentiment-internlm-20b-8epochs-lr2e-4-linear 
+--base_model internlm-20b 
+--dataset data/fingpt-sentiment-train 
+--max_length 512 
+--batch_size 8 
+--learning_rate 2e-4 
+--num_epochs 8 
+> train_internlm-20b_1gpu_8epochs_lr2e4_bs8_fp16_linear.log 2>&1
+```
+
+## Training Data:
+
+* https://huggingface.co/datasets/FinGPT/fingpt-sentiment-train
+- PEFT 0.5.0