Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+# Phi-2 QLoRA Fine-tuned Assistant
+
+This is a fine-tuned version of Microsoft's Phi-2 model using QLoRA (Quantized Low-Rank Adaptation). The model has been trained to provide helpful responses for various tasks including coding, writing, and general assistance.
+
+## Model Details
+
+- **Base Model**: Microsoft Phi-2 (2.7B parameters)
+- **Fine-tuning Method**: QLoRA (4-bit quantization)
+- **Training Data**: Custom dataset focused on programming and professional communication
+- **Hardware Used**: NVIDIA RTX 4090 (24GB VRAM)
+
+## Usage
+
+You can interact with the model through the Gradio interface by visiting the "Spaces" tab of this repository.
+
+### Local Installation
+
+To run the model locally:
+
+1. Clone this repository
+2. Install dependencies:
+```bash
+pip install -r requirements.txt
+```
+3. Run the Gradio app:
+```bash
+python gradio_app.py
+```
+
+### Parameters
+
+- **Max Length**: Controls the maximum length of the generated response (64-1024 tokens)
+- **Temperature**: Controls randomness in generation (0.1-1.0)
+- **Top P**: Controls diversity of generated responses (0.1-1.0)
+
+## Example Prompts
+
+1. "Write a Python function to calculate the factorial of a number"
+2. "Explain the concept of machine learning in simple terms"
+3. "Write a professional email requesting a meeting with a client"
+
+## Limitations
+
+- The model works best with English language input
+- Response quality may vary depending on the complexity of the prompt
+- Maximum context length is limited to 2048 tokens
+
+## License
+
+This model is subject to the Microsoft Phi-2 license terms and conditions.
+
+## Acknowledgments
+
+- Microsoft for the Phi-2 base model
+- Hugging Face for the transformers library and model hosting
+- The QLoRA paper authors for the quantization technique 

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "fc1",
+    "dense",
+    "fc2"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bdedfb9b1ba2f11552779be38126aac433a079a8a8434c24804322de0a06d1a
+size 618916216

gradio_app.py

@@ -0,0 +1,70 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
+
+# Load the base model and tokenizer
+base_model_name = "microsoft/phi-2"
+adapter_path = "./output"  # Path to your trained LoRA adapter
+
+def load_model():
+    print("Loading model and tokenizer...")
+    tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        base_model_name,
+        torch_dtype=torch.float16,
+        device_map="auto",
+        trust_remote_code=True
+    )
+    
+    # Load the LoRA adapter
+    model = PeftModel.from_pretrained(model, adapter_path)
+    return model, tokenizer
+
+# Load the model and tokenizer
+model, tokenizer = load_model()
+
+def generate_response(prompt, max_length=512, temperature=0.7, top_p=0.9):
+    """Generate a response using the fine-tuned model."""
+    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
+    inputs = {k: v.to(model.device) for k, v in inputs.items()}
+    
+    # Generate response
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_length=max_length,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=True,
+            pad_token_id=tokenizer.pad_token_id,
+            eos_token_id=tokenizer.eos_token_id
+        )
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    # Remove the prompt from the response
+    if response.startswith(prompt):
+        response = response[len(prompt):].strip()
+    return response
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(label="Enter your prompt", lines=4),
+        gr.Slider(minimum=64, maximum=1024, value=512, label="Max Length"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, label="Top P"),
+    ],
+    outputs=gr.Textbox(label="Generated Response", lines=8),
+    title="Phi-2 QLoRA Fine-tuned Assistant",
+    description="Enter a prompt to generate a response using the fine-tuned Phi-2 model.",
+    examples=[
+        ["Write a Python function to calculate the factorial of a number"],
+        ["Explain the concept of machine learning in simple terms"],
+        ["Write a professional email requesting a meeting with a client"],
+    ]
+)
+
+if __name__ == "__main__":
+    demo.launch(share=True) 

requirements.txt

@@ -0,0 +1,17 @@
+gradio>=4.0.0
+torch>=2.0.0
+transformers>=4.36.0
+peft>=0.7.0
+accelerate>=0.25.0
+bitsandbytes>=0.41.0
+datasets>=2.14.0
+wandb>=0.15.10
+sentencepiece>=0.1.99
+einops>=0.6.1
+scipy>=1.11.3
+tqdm>=4.66.1
+huggingface_hub>=0.17.3
+pandas>=2.0.0
+numpy>=1.24.0
+rouge-score>=0.1.2
+nltk>=3.8.1 

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,326 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}