Upload 2 files

Scripts/Inference_llama.cpp.py

@@ -0,0 +1,33 @@
+from llama_cpp import Llama
+
+# Insert your research topic here
+RESEARCH_TOPIC = """
+
+"""
+
+model_path = "./" # Path to the directory containing your model weight files
+
+llm = Llama(
+    model_path=model_path,
+    n_gpu_layers=33, 
+    n_ctx=2048,
+    n_threads=4
+)
+
+topic = RESEARCH_TOPIC.strip()
+prompt = f"USER: Research Topic: \"{topic}\"\nLet's think step by step:\nASSISTANT:"
+
+
+output = llm(
+    prompt,
+    max_tokens=2000,
+    temperature=0.7,
+    top_p=0.9,
+    repeat_penalty=1.1
+)
+
+result = output.get("choices", [{}])[0].get("text", "").strip()
+
+print(result)
+
+

Scripts/Inference_safetensors.py

@@ -0,0 +1,50 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Insert your research topic here
+RESEARCH_TOPIC = """
+
+"""
+
+def load_model(model_path):
+    model = AutoModelForCausalLM.from_pretrained(
+        model_path,
+        torch_dtype=torch.float16,
+        device_map="auto"
+    )
+    
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    
+    return model, tokenizer
+
+def generate_response(model, tokenizer, topic):
+    topic = topic.strip()
+    
+    prompt = f"USER: Research Topic: \"{topic}\"\nLet's think step by step:\nASSISTANT:"
+    
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=2000,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=1.1,
+        do_sample=True
+    )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    return response.split("ASSISTANT:")[-1].strip()
+
+def main():
+    model_path = "./" # Path to the directory containing your model weight files
+    
+    model, tokenizer = load_model(model_path)
+    
+    result = generate_response(model, tokenizer, RESEARCH_TOPIC)
+    
+    print(result)
+
+if __name__ == "__main__":
+    main()