Update README.md

README.md

@@ -63,24 +63,38 @@ The model is fine-tuned on specific data (cryptocurrency news and price data) an
 To start using the model for predictions, you can follow the example code below:
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
 
-# Load the fine-tuned model
-model_name = "agarkovv/CryptoTrader-LM"
-model = AutoModelForCausalLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+from huggingface_hub import login
+login("YOUR TOKEN HERE")
 
-# Example input: news articles and price data
-input_text = "[INST]Bitcoin price surges as ETF approval rumors circulate...[/INST]"
 
-# Tokenize and generate prediction
-inputs = tokenizer(input_text, return_tensors="pt")
-outputs = model.generate(**inputs)
+PROMPT = "[INST]YOUR PROMPT HERE[/INST]"
+MAX_LENGTH = 32768  # Do not change
+DEVICE = "cpu"
 
-# Decode the output for trading decision (buy, sell, or hold)
-decision = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(f"Trading decision: {decision}")
+
+model_id = "agarkovv/CryptoTrader-LM"
+base_model_id = "mistralai/Ministral-8B-Instruct-2410"
+
+model = AutoPeftModelForCausalLM.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+
+model = model.to(DEVICE)
+model.eval()
+inputs = tokenizer(
+    PROMPT, return_tensors="pt", padding=False, max_length=MAX_LENGTH, truncation=True
+)
+inputs = {key: value.to(model.device) for key, value in inputs.items()}
+
+res = model.generate(
+    **inputs,
+    use_cache=True,
+    max_new_tokens=MAX_LENGTH,
+)
+output = tokenizer.decode(res[0], skip_special_tokens=True)
+print(output)
 ```
 
 ## Training Details