Update README.md

README.md

@@ -1,209 +1,181 @@
 ---
+license: llama3
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
-library_name: peft
-pipeline_tag: text-generation
 tags:
-- base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
-- dpo
-- lora
-- transformers
-- trl
+- RAG hallucinations
+- Knowledge Conflict
+datasets:
+- qiaojin/PubMedQA
+- Salesforce/FaithEval-counterfactual-v1.0
+- wandb/RAGTruth-processed
+metrics:
+- accuracy
 ---
 
-# Model Card for Model ID
+# CopyPasteLLM-L3-8B
+
+## Quick Start
+
+### Method 1: Using Transformers
+
+```python
+#!/usr/bin/env python3
+import torch
+from transformers import (
+    AutoTokenizer, 
+    AutoModelForCausalLM, 
+    BitsAndBytesConfig,
+    pipeline
+)
+import warnings
+warnings.filterwarnings("ignore")
+
+def load_model_and_tokenizer():
+    """Load model and tokenizer"""
+    print("Loading model and tokenizer...")
+    
+    # Base model configuration
+    base_model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
+    lora_model_name = "wingchiuloong/CopyPasteLLM-L3-8B"
+    
+    # Quantization configuration
+    quantization_config = BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_compute_dtype=torch.float16,
+        bnb_4bit_use_double_quant=True,
+        bnb_4bit_quant_type="nf4"
+    )
+    
+    # Load tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(
+        base_model_name,
+        trust_remote_code=True
+    )
+    
+    # Load base model
+    model = AutoModelForCausalLM.from_pretrained(
+        base_model_name,
+        quantization_config=quantization_config,
+        device_map="auto",
+        trust_remote_code=True,
+        torch_dtype=torch.float16
+    )
+    
+    # Load LoRA weights
+    print("Loading LoRA weights...")
+    from peft import PeftModel
+    model = PeftModel.from_pretrained(model, lora_model_name)
+    
+    return model, tokenizer
+
+def create_pipeline(model, tokenizer):
+    """Create inference pipeline"""
+    return pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        torch_dtype=torch.float16,
+        device_map="auto"
+    )
+
+def format_prompt(user_input):
+    """Format input to Llama-3 format"""
+    system_message = "You are a helpful AI assistant."
+    
+    prompt = f"""<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{user_input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+"""
+    return prompt
+
+def main():
+    """Main function - One-time inference"""
+    print("CopyPasteLLM inference Demo")
+    print("=" * 50)
+    
+    # Set test question
+    context = "Galileo Galilei, renowned as one of the most influential figures in the history of science, made numerous contributions that revolutionized our understanding of physics and astronomy. His meticulous work with telescopes led to groundbreaking discoveries about the moons of Jupiter and the phases of Venus. Beyond the realm of astronomy, his observations and experiments laid the foundation for classical mechanics. One of Galileo’s lesser-known achievements is his development of the Three Laws of Motion, which were critical in advancing the study of kinematics and dynamics. These laws articulate the principles of inertia, the relationship between force and motion, and the law of action and reaction, providing a comprehensive framework for understanding moving bodies. His work on pendulums also contributed substantially to timekeeping and horology, as he discovered that pendulums of different lengths oscillate at predictable periods, a principle still applied in modern clocks. Galileo’s interdisciplinary approach enabled him to synthesize knowledge from various fields, which allowed new theories to emerge, reshaping the scientific landscape of his time and beyond. Notably, his support of the heliocentric model of the solar system earned him both acclaim and censure, highlighting the tension between scientific inquiry and established doctrine. In contrast to Galen’s biological studies and Newton’s later contributions, Galileo’s articulation of the Three Laws of Motion was pivotal in the transition from Aristotelian physics to Newtonian mechanics. His contributions remain a testament to the interplay of observation, theory, and experimentation in scientific progress."
+    question = "Which law was Galileo Galilei responsible for describing?"
+    test_question = f"{context}\nQ: {question}\nA:"
+    print(f"{test_question}")
+    print("-" * 50)
+    
+    try:
+        # Load model
+        model, tokenizer = load_model_and_tokenizer()
+        
+        # Create pipeline
+        print("Creating inference pipeline...")
+        pipe = create_pipeline(model, tokenizer)
+        
+        print("Model loaded! Starting inference...")
+        
+        # Format input
+        prompt = format_prompt(test_question)
+        
+        # Generate reply
+        print("Generating reply...")
+        outputs = pipe(
+            prompt,
+            max_new_tokens=512,
+            temperature=1.0,
+            top_p=0.95,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id,
+            eos_token_id=tokenizer.eos_token_id,
+            return_full_text=False
+        )
+        
+        # Output result
+        response = outputs[0]['generated_text']
+        print(f"\nCopyPasteLLM:\n{response}") # According to the passage, Galileo Galilei was responsible for describing the Three Laws of Motion, which articulate the principles of inertia, the relationship between force and motion, and the law of action and reaction.
+                
+    except Exception as e:
+        print(f"Inference failed: {e}")
+        print("Please ensure the necessary dependencies are installed: pip install transformers peft bitsandbytes accelerate")
+
+if __name__ == "__main__":
+    main()
+```
+
+### Method 2: Using vLLM
+
+```bash
+base_model="meta-llama/Meta-Llama-3-8B-Instruct"
+lora_modules_path="<model_at_your_huggingface_cache>" # like "~/.huggingface/hub/models--wingchiuloong--CopyPasteLLM-L3-8B/snapshots/<uuid>"
+
+python -m vllm.entrypoints.openai.api_server \
+  --model $base_model \
+  --enable-lora \
+  --max-lora-rank 64 \
+  --lora-modules CopyPasteLLM-8b=$lora_modules_path \
+  --host 0.0.0.0 \
+  --port 8888 \
+  --gpu-memory-utilization 0.8 \
+  --max-model-len 1024 \
+  --max-num-seqs 32 \
+  --tensor-parallel-size 1
+```
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+Coming soon...
+```
+
+## License
+
+This model is released under the same license as the base Llama-3-8B-Instruct model. Please refer to the [Llama 3 Community License](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for details.
+
+## Contact
+
+For questions and support, please open an issue on the [GitHub repository](https://github.com/longyongchao/CopyPasteLLM).
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
+---
 
-- PEFT 0.16.0
+**Note**: This model is designed for research and educational purposes. Please ensure responsible use and compliance with applicable laws and regulations.