Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,38 @@
+# new2
+
+This is a LORA adapter fine-tuned on the base model [NousResearch/DeepHermes-3-Llama-3-3B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-3B-Preview).
+
+## Model Details
+- **Base Model:** NousResearch/DeepHermes-3-Llama-3-3B-Preview
+- **Adapter Type:** LORA
+- **Task:** JEE Mathematics 3D Geometry Problem
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# Load base model and tokenizer
+base_model = "NousResearch/DeepHermes-3-Llama-3-3B-Preview"
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.bfloat16)
+
+# Load the LoRA adapter
+adapter_model = "AthenaAgent42/new2"
+model = PeftModel.from_pretrained(model, adapter_model)
+
+# Example prompt
+prompt = """
+<Your prompt here>
+"""
+
+# Generate response
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+outputs = model.generate(input_ids, max_new_tokens=512)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+