Upload 10 files

app.py

@@ -0,0 +1,138 @@
+import gradio as gr
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import os
+
+# --- Configuration ---
+BASE_MODEL_NAME = "microsoft/phi-2"
+# Path to your adapters. 
+# For a real HF Space, you would typically upload the adapter files to the Space 
+# and prompt the path relative to the root, e.g., "./adapter_model"
+ADAPTER_PATH = "./model_adapters" 
+
+print("Initializing Model...")
+
+# Check for CUDA
+if torch.cuda.is_available():
+    device = "cuda"
+    print(f"Using GPU: {torch.cuda.get_device_name(0)}")
+else:
+    device = "cpu"
+    print("Using CPU")
+
+# Determine dtype
+compute_dtype = torch.float32
+if device == "cuda":
+    if torch.cuda.is_bf16_supported():
+        compute_dtype = torch.bfloat16
+        print("Using bfloat16")
+    else:
+        compute_dtype = torch.float16
+        print("Using float16")
+
+# Load Tokenizer
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL_NAME, trust_remote_code=True)
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = "left"
+
+# Load Model
+try:
+    print(f"Loading base model {BASE_MODEL_NAME}...")
+    base_model = AutoModelForCausalLM.from_pretrained(
+        BASE_MODEL_NAME,
+        torch_dtype=compute_dtype,
+        device_map=device,
+        trust_remote_code=True
+    )
+    
+    print(f"Check for adapters at {ADAPTER_PATH}")
+    if os.path.exists(ADAPTER_PATH):
+        print(f"Loading adapters from {ADAPTER_PATH}...")
+        model = PeftModel.from_pretrained(base_model, ADAPTER_PATH)
+    else:
+        print(f"WARNING: Adapter path {ADAPTER_PATH} not found. Using base model only.")
+        model = base_model
+        
+    model.eval()
+    print("Model loaded successfully.")
+    
+except Exception as e:
+    print(f"Error loading model: {e}")
+    raise e
+
+def generate_response(prompt, temperature, top_p, max_new_tokens):
+    try:
+        inputs = tokenizer(prompt, return_tensors="pt").to(device)
+        
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_new_tokens=max_new_tokens,
+                do_sample=True,
+                temperature=temperature,
+                top_p=top_p,
+                pad_token_id=tokenizer.pad_token_id,
+                eos_token_id=tokenizer.eos_token_id
+            )
+            
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        # Optional: Clean up response if it repeats the prompt (usually model does)
+        # response = response[len(prompt):] 
+        return response
+        
+    except Exception as e:
+        return f"Error during generation: {str(e)}"
+
+# --- Gradio UI ---
+with gr.Blocks(title="Phi-2 GRPO Fine-tuned Model") as demo:
+    gr.Markdown("# Phi-2 GRPO Assistant")
+    gr.Markdown("Query the fine-tuned Phi-2 model. Assuming adapters are in `./model_adapters`.")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            prompt_input = gr.Textbox(
+                label="Input Prompt", 
+                lines=5, 
+                placeholder="Enter your prompt here..."
+            )
+            
+            with gr.Accordion("Hyperparameters", open=True):
+                temp_slider = gr.Slider(
+                    minimum=0.1, maximum=2.0, value=0.7, step=0.1, 
+                    label="Temperature (Creativity)"
+                )
+                top_p_slider = gr.Slider(
+                    minimum=0.1, maximum=1.0, value=0.9, step=0.05, 
+                    label="Top-p (Nucleus Sampling)"
+                )
+                max_tokens_slider = gr.Slider(
+                    minimum=16, maximum=512, value=200, step=16, 
+                    label="Max New Tokens"
+                )
+            
+            submit_btn = gr.Button("Generate", variant="primary")
+            
+        with gr.Column(scale=1):
+            output_box = gr.Textbox(label="Model Response", lines=10, interactive=False)
+            
+    # Sample Inputs
+    examples = gr.Examples(
+        examples=[
+            ["Explain quantum computing to a high school student."],
+            ["Write a Python function to quicksort a list."],
+            ["What are the health benefits of meditation?"],
+            ["Traduce 'Hello, how are you?' al español."],
+            ["Create a story about a robot who wants to be a chef."]
+        ],
+        inputs=prompt_input
+    )
+
+    submit_btn.click(
+        fn=generate_response,
+        inputs=[prompt_input, temp_slider, top_p_slider, max_tokens_slider],
+        outputs=output_box
+    )
+
+if __name__ == "__main__":
+    demo.launch()

model_adapters/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "Wqkv",
+    "out_proj",
+    "fc1"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model_adapters/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ccc9ef726ea1285e3cd6a13a563be50f38c43159563943a1f09c8f225f30af
+size 52444936

model_adapters/added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

model_adapters/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
+  }
+}

model_adapters/tokenizer_config.json

@@ -0,0 +1,328 @@
+{
+  "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|>",
+  "padding_side": "left",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<|endoftext|>"
+}

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+torch
+transformers
+peft
+einops
+accelerate
+scipy