Initial setup with fine-tuned model and application code

app/main.py

@@ -0,0 +1,43 @@
+from .utils import format_prompt_for_hint, format_prompt_for_followup
+from .model_handler import generate_hint, generate_follow_up, generate_feedback # Add generate_feedback
+import re # Import regex module
+
+def clean_task_description(description: str) -> str:
+    """Removes common example, constraint, input/output format sections by finding the first occurrence."""
+    lines = description.splitlines()
+    cleaned_lines = []
+    skip_keywords = ["Example:", "Input:", "Output:", "Constraints:", "Input Format:", "Output Format:", "Explanation:"]
+    first_skip_index = -1
+
+    # Find the index of the first line starting with a skip keyword
+    for i, line in enumerate(lines):
+        line_stripped_lower = line.strip().lower()
+        if any(line_stripped_lower.startswith(keyword.lower()) for keyword in skip_keywords):
+            first_skip_index = i
+            break # Stop at the first occurrence
+
+    # If a skip keyword was found, take lines before it
+    if first_skip_index != -1:
+        cleaned_lines = lines[:first_skip_index]
+    # Otherwise, keep all lines (no skip keywords found)
+    else:
+        cleaned_lines = lines
+
+    # Join back the relevant lines and strip whitespace
+    return "\n".join(cleaned_lines).strip()
+
+
+def get_hint(code, task_description, mode='concise'): # Add mode
+    cleaned_description = clean_task_description(task_description)
+    # Pass mode to generate_hint
+    return generate_hint(code, cleaned_description, mode)
+
+def get_feedback(code, task_description, mode='concise'): # New function
+    cleaned_description = clean_task_description(task_description)
+    # Call generate_feedback with mode
+    return generate_feedback(code, cleaned_description, mode)
+
+def get_follow_up_question(code, task_description):
+    cleaned_description = clean_task_description(task_description)
+    # Pass code to generate_follow_up (already updated in model_handler)
+    return generate_follow_up(cleaned_description, code) # Pass both args

app/model_handler.py

@@ -0,0 +1,99 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from .utils import format_prompt_for_hint, format_prompt_for_followup, format_prompt_for_feedback
+from peft import PeftModel, PeftConfig
+
+MODEL_NAME = "Salesforce/codegen-350M-mono"
+LORA_PATH = "C:/Users/yaswa/OneDrive/Desktop/New folder/Fine-tuning-data/fine-tuned-model"
+
+# Initialize the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
+
+# Load the base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True
+)
+
+# Load and apply the LoRA adapter
+model = PeftModel.from_pretrained(
+    base_model,
+    LORA_PATH,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# Merge LoRA weights with base model for better inference performance (optional)
+model = model.merge_and_unload()
+
+def generate_hint(code_snippet, task_description, mode='concise'):
+    prompt = format_prompt_for_hint(task_description, code_snippet, mode)
+    print("--- PROMPT SENT TO MODEL ---")
+    print(prompt)
+    print("-----------------------------")
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs,  max_new_tokens=128, do_sample=True, temperature=0.7)
+    decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("--- RAW MODEL OUTPUT ---")
+    print(decoded_output)
+    print("------------------------")
+    # Extract only what comes after 'HINT:'
+    if "HINT:" in decoded_output:
+        hint = decoded_output.split("HINT:", 1)[-1].strip()
+        for line in hint.splitlines():
+            if line.strip():
+                return line.strip()
+    # Fallback: return first non-empty line not in prompt
+    lines = [line.strip() for line in decoded_output.splitlines() if line.strip()]
+    for line in lines:
+        if "Task Description" not in line and "User's Code" not in line and "AI-HR Assistant" not in line:
+            return line
+    return ""
+
+def generate_feedback(code_snippet, task_description, mode='concise'):
+    prompt = format_prompt_for_feedback(task_description, code_snippet, mode)
+    print("--- PROMPT SENT TO MODEL (FEEDBACK) ---")
+    print(prompt)
+    print("---------------------------------------")
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=256 if mode == 'detailed' else 128, do_sample=True, temperature=0.75)
+    decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("--- RAW MODEL OUTPUT (FEEDBACK) ---")
+    print(decoded_output)
+    print("-----------------------------------")
+    # Extract only what comes after 'FEEDBACK:'
+    if "FEEDBACK:" in decoded_output:
+        feedback = decoded_output.split("FEEDBACK:", 1)[-1].strip()
+        return feedback
+    # Fallback: return first non-empty line not in prompt
+    lines = [line.strip() for line in decoded_output.splitlines() if line.strip()]
+    for line in lines:
+        if "Task Description" not in line and "User's Code" not in line and "AI-HR Assistant" not in line:
+            return line
+    return ""
+
+def generate_follow_up(task_description, code_snippet):
+    prompt = format_prompt_for_followup(task_description, code_snippet)
+    print("--- PROMPT SENT TO MODEL ---")
+    print(prompt)
+    print("-----------------------------")
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs,  max_new_tokens=128, do_sample=True, temperature=0.7)
+    decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("--- RAW MODEL OUTPUT ---")
+    print(decoded_output)
+    print("------------------------")
+    # Extract only what comes after the prompt
+    if prompt in decoded_output:
+        followup = decoded_output.split(prompt, 1)[-1].strip()
+        for line in followup.splitlines():
+            if line.strip():
+                return line.strip()
+    # Fallback: return first non-empty line not in prompt
+    lines = [line.strip() for line in decoded_output.splitlines() if line.strip()]
+    for line in lines:
+        if "Task Description" not in line and "User's Code" not in line and "AI-HR Assistant" not in line:
+            return line
+    return ""

app/utils.py

@@ -0,0 +1,38 @@
+def format_prompt_for_hint(task_description: str, code_snippet: str, mode: str = 'concise') -> str:
+    instruction = (
+        "Provide a concise, helpful hint based on the user's code (no code, only conceptual advice or guiding question) in one line."
+        if mode == 'concise'
+        else "Provide a detailed, helpful hint (conceptual advice, guiding questions, or pointing to specific areas to check) to help the user solve the problem. Do not provide the full code solution."
+    )
+    return (
+        f"Task Description:\n{task_description}\n\n"
+        f"User's Code:\n{code_snippet}\n\n"
+        f"You are an AI-HR Assistant. {instruction}\n"
+        "HINT:"
+    )
+
+
+def format_prompt_for_feedback(task_description: str, code_snippet: str, mode: str = 'concise') -> str:
+    instruction = (
+        "Provide concise feedback on the user's code approach, identifying potential issues or areas for improvement in 1-2 sentences."
+        if mode == 'concise'
+        else "Provide detailed feedback on the user's code. Analyze its correctness, efficiency, style, and potential edge cases. Suggest specific improvements or alternative approaches if applicable. Do not provide the full corrected code."
+    )
+    return (
+        f"Task Description:\n{task_description}\n\n"
+        f"User's Code:\n{code_snippet}\n\n"
+        f"You are an AI-HR Assistant. {instruction}\n"
+        "FEEDBACK:"
+    )
+
+
+def format_prompt_for_followup(task_description: str, code_snippet: str) -> str:
+    return (
+        f"Task Description:\n{task_description}\n\n"
+        f"User's Code:\n{code_snippet}\n\n"
+        "You are an AI-HR Assistant. Based on the user's code, create a *follow-up* question that:\n"
+        "- Encourages deeper thinking about the submitted code.\n"
+        "- Asks about possible optimizations, improvements, edge cases, time complexity, or alternative approaches.\n"
+        "- Is related directly to the user's code (not a new or different task).\n"
+        "- The question should be open-ended and thought-provoking."
+    )

fine-tuned-model/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Salesforce/codegen-350M-mono
+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 0.15.2

fine-tuned-model/adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Salesforce/codegen-350M-mono",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc_in",
+    "fc_out",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

fine-tuned-model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3728181c06dbd133b08d5ad53fbce71f2ea571d1bfc0ac5bdb28b762057282e8
+size 9190312

fine-tuned-model/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
+}

fine-tuned-model/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
+  }
+}

fine-tuned-model/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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

requirements.txt

@@ -0,0 +1,9 @@
+fastapi
+uvicorn
+transformers
+torch
+peft
+accelerate
+sentencepiece
+python-multipart
+gradio