spaces init

app.py

@@ -0,0 +1,127 @@
+import streamlit as st
+import torch
+from model_handler import load_model_and_tokenizer, generate_response
+import time
+
+# Page configuration
+st.set_page_config(
+    page_title="Phi-2 Fine-tuned Assistant",
+    page_icon="🤖",
+    layout="centered"
+)
+
+# Custom CSS for chat interface
+st.markdown("""
+<style>
+.user-bubble {
+    background-color: #e6f7ff;
+    border-radius: 15px;
+    padding: 10px 15px;
+    margin: 5px 0;
+    max-width: 80%;
+    margin-left: auto;
+    margin-right: 10px;
+    position: relative;
+}
+.assistant-bubble {
+    background-color: #f0f0f0;
+    border-radius: 15px;
+    padding: 10px 15px;
+    margin: 5px 0;
+    max-width: 80%;
+    margin-left: 10px;
+    position: relative;
+}
+.chat-container {
+    display: flex;
+    flex-direction: column;
+    height: calc(100vh - 200px);
+    overflow-y: auto;
+    padding: 10px;
+    margin-bottom: 20px;
+}
+.stTextInput>div>div>input {
+    border-radius: 20px;
+}
+.stButton>button {
+    border-radius: 20px;
+    width: 100%;
+}
+</style>
+""", unsafe_allow_html=True)
+
+# Initialize session state for chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+if "model_loaded" not in st.session_state:
+    st.session_state.model_loaded = False
+
+# App title
+st.title("Phi-2 Fine-tuned Assistant")
+
+# Load model (only once)
+if not st.session_state.model_loaded:
+    with st.spinner("Loading the fine-tuned model... This may take a minute."):
+        model, tokenizer = load_model_and_tokenizer()
+        st.session_state.model = model
+        st.session_state.tokenizer = tokenizer
+        st.session_state.model_loaded = True
+        st.success("Model loaded successfully!")
+
+# Display chat messages
+st.markdown('<div class="chat-container">', unsafe_allow_html=True)
+for message in st.session_state.messages:
+    role = message["role"]
+    content = message["content"]
+    
+    if role == "user":
+        st.markdown(f'<div class="user-bubble">{content}</div>', unsafe_allow_html=True)
+    else:
+        st.markdown(f'<div class="assistant-bubble">{content}</div>', unsafe_allow_html=True)
+st.markdown('</div>', unsafe_allow_html=True)
+
+# Chat input
+with st.container():
+    user_input = st.text_input("Your message:", key="user_input", placeholder="Type your message here...")
+    
+    # Process input when user submits a message
+    if user_input:
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "user", "content": user_input})
+        
+        # Create a placeholder for the assistant's response
+        assistant_response_placeholder = st.empty()
+        
+        # Generate streaming response
+        full_response = ""
+        
+        # Display "Assistant is typing..." message
+        with assistant_response_placeholder.container():
+            st.markdown('<div class="assistant-bubble">Assistant is typing...</div>', unsafe_allow_html=True)
+        
+        # Generate response with streaming
+        for token in generate_response(
+            st.session_state.model, 
+            st.session_state.tokenizer, 
+            user_input  # Changed to pass just the current input
+        ):
+            full_response += token
+            # Update the response in real-time
+            with assistant_response_placeholder.container():
+                st.markdown(f'<div class="assistant-bubble">{full_response}</div>', unsafe_allow_html=True)
+            time.sleep(0.01)  # Small delay to make streaming visible
+        
+        # Add assistant's response to chat history
+        st.session_state.messages.append({"role": "assistant", "content": full_response})
+        
+        # Clear the input box
+        st.session_state.user_input = ""
+        
+        # Rerun to update the UI
+        st.experimental_rerun()
+
+# Add a button to clear the chat
+if st.button("Clear Chat"):
+    st.session_state.messages = []
+    st.experimental_rerun()

model_handler.py

@@ -0,0 +1,106 @@
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+def load_model_and_tokenizer():
+    """Load the fine-tuned model and tokenizer, ensuring CPU compatibility."""
+    # Load tokenizer
+    base_model_name = "microsoft/phi-2"
+    tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+    tokenizer.pad_token = tokenizer.eos_token
+    
+    # Load base model on CPU
+    base_model = AutoModelForCausalLM.from_pretrained(
+        base_model_name,
+        torch_dtype=torch.float32,  # Use float32 for CPU
+        device_map="auto"
+    )
+    
+    # Load adapter weights
+    model = PeftModel.from_pretrained(
+        base_model, 
+        "phi2-grpo-qlora-final",
+        device_map="auto"
+    )
+    
+    # Set to evaluation mode
+    model.eval()
+    
+    return model, tokenizer
+
+def generate_response(model, tokenizer, prompt, max_new_tokens=256):
+    """Generate a streaming response from the model for the given prompt."""
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    # Store the input length to identify the response part
+    input_length = len(tokenizer.decode(inputs.input_ids[0], skip_special_tokens=True))
+    
+    # Initialize generation
+    generated_ids = inputs.input_ids.clone()
+    past_key_values = None
+    response_text = ""
+    
+    # Add stop sequences to detect natural endings
+    stop_sequences = ["\n\n", "\nExercise:", "\nQuestion:"]
+    
+    # Generate tokens one by one
+    for _ in range(max_new_tokens):
+        with torch.no_grad():
+            # Forward pass
+            outputs = model(
+                input_ids=generated_ids[:, -1:] if past_key_values is not None else generated_ids,
+                past_key_values=past_key_values,
+                use_cache=True
+            )
+            
+            # Get logits and past key values
+            logits = outputs.logits
+            past_key_values = outputs.past_key_values
+            
+            # Sample next token
+            next_token_logits = logits[:, -1, :]
+            next_token_logits = next_token_logits / 0.7  # Apply temperature
+            
+            # Apply top-p sampling
+            sorted_logits, sorted_indices = torch.sort(next_token_logits, descending=True)
+            cumulative_probs = torch.cumsum(torch.softmax(sorted_logits, dim=-1), dim=-1)
+            sorted_indices_to_remove = cumulative_probs > 0.9
+            sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
+            sorted_indices_to_remove[..., 0] = 0
+            
+            indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
+            next_token_logits[indices_to_remove] = -float('Inf')
+            
+            # Sample from the filtered distribution
+            probs = torch.softmax(next_token_logits, dim=-1)
+            next_token = torch.multinomial(probs, num_samples=1)
+            
+            # Append to generated ids
+            generated_ids = torch.cat([generated_ids, next_token], dim=-1)
+            
+            # Decode the current token
+            current_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+            
+            # Extract only the new part (response)
+            if len(current_text) > input_length:
+                new_text = current_text[input_length:]
+                # Get only the new characters
+                new_chars = new_text[len(response_text):]
+                response_text = new_text
+                
+                # Yield the new characters for streaming
+                yield new_chars
+            
+            # Stop if we generate an EOS token
+            if next_token[0, 0].item() == tokenizer.eos_token_id:
+                break
+                
+            # Check for natural stopping points
+            if any(stop_seq in response_text for stop_seq in stop_sequences):
+                # If we find a stop sequence, only keep text up to that point
+                for stop_seq in stop_sequences:
+                    if stop_seq in response_text:
+                        stop_idx = response_text.find(stop_seq)
+                        if stop_idx > 0:  # Only trim if we have some content
+                            yield response_text[len(response_text)-1:stop_idx]  # Yield any remaining text
+                            return

phi2-grpo-qlora-final/README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- 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 0.15.1

phi2-grpo-qlora-final/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "bias": "none",
+  "corda_config": null,
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

phi2-grpo-qlora-final/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df026300049caa8adbd34d1d70b6566fac13f6595733764665074c68f3375b3c
+size 31483040

phi2-grpo-qlora-final/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
+}

phi2-grpo-qlora-final/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
+  }
+}

phi2-grpo-qlora-final/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|>"
+}

phi2-grpo-qlora-final/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbb41e102fe1e42e0e75d61ec81ed3b5f752bf1cfa19bf78eda486554e47da3
+size 6072

requirements.txt

@@ -0,0 +1,5 @@
+streamlit==1.44.1
+torch>=2.0.0
+transformers>=4.30.0
+peft>=0.4.0
+accelerate>=0.20.0