add gradio spaces

app.py

@@ -0,0 +1,95 @@
+# Import libraries
+import json
+from pathlib import Path
+
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from peft import PeftModel
+
+
+# Define path
+MODEL_DIR = Path("model")
+META_PATH = Path("preprocess_meta.json")
+THRESH_PATH = MODEL_DIR / "threshold_global.json"
+
+# Load metadata
+with META_PATH.open() as f:
+    meta = json.load(f)
+
+label2id = meta["label2id"]
+id2label = {int(i): label for label, i in label2id.items()}
+labels = [id2label[i] for i in range(len(id2label))]
+max_length = meta["max_length"]
+
+
+with THRESH_PATH.open() as f:
+    GLOBAL_THRESHOLD = json.load(f)["global_threshold"]
+
+# Load model + LoRA adapters (handles both plain + adapter cases)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
+base_model = AutoModelForSequenceClassification.from_pretrained(
+    MODEL_DIR, trust_remote_code=True
+)
+try:
+    model = PeftModel.from_pretrained(base_model, MODEL_DIR, is_trainable=False)
+except ValueError:
+    # already merged
+    model = base_model
+
+model.eval()
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+
+def preprocess(subject: str, body: str) -> str:
+    sep = tokenizer.sep_token if tokenizer.sep_token else " "
+    text = f"{subject.strip()} {sep} {body.strip()}".strip()
+    return text
+
+def predict_intents(subject: str, body: str):
+    if not subject and not body:
+        return {"Predicted labels": [], "Scores": {}}
+
+    text = preprocess(subject, body)
+    inputs = tokenizer(
+        text,
+        truncation=True,
+        max_length=max_length,
+        return_tensors="pt"
+    )
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+
+    with torch.no_grad():
+        logits = model(**inputs).logits.squeeze().float()
+        probs = torch.sigmoid(logits).cpu().numpy()
+
+    scores = {label: float(prob) for label, prob in zip(labels, probs)}
+    predicted = [label for label, prob in scores.items() if prob >= GLOBAL_THRESHOLD]
+
+    return {
+        "Predicted labels": predicted or ["No label ≥ threshold"],
+        "Scores": scores,
+    }
+
+
+demo = gr.Interface(
+    fn=predict_intents,
+    inputs=[
+        gr.Textbox(label="Subject", placeholder="Email subject"),
+        gr.Textbox(label="Body", lines=12, placeholder="Email body"),
+    ],
+    outputs=gr.JSON(label="Result (labels & probabilities)"),
+    title="Multi-Label Email Intent Classifier",
+    description=(
+        "DistilBERT + LoRA fine-tuned on synthetic email intents. "
+        "Predictions use a global sigmoid threshold of {:.2f}.".format(GLOBAL_THRESHOLD)
+    ),
+    examples=[
+        ["Meeting Reminder: Project Sync", "Dear team, this is a reminder for tomorrow's sync at 10 AM."],
+        ["Travel Booking Confirmation", "Your flight to London on 12 June has been confirmed. See attached itinerary."],
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()

model/README.md

@@ -0,0 +1,206 @@
+---
+base_model: distilbert-base-uncased
+library_name: peft
+tags:
+- base_model:adapter:distilbert-base-uncased
+- lora
+- transformers
+---
+
+# 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 0.17.1

model/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "DistilBertForSequenceClassification",
+    "parent_library": "transformers.models.distilbert.modeling_distilbert"
+  },
+  "base_model_name_or_path": "distilbert-base-uncased",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "ffn.lin2",
+    "v_lin",
+    "ffn.lin1",
+    "out_lin",
+    "k_lin",
+    "q_lin"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498f13cad864edbea083d82fc806518741c5dcd91d6fb39f33a3c72d34c4aea1
+size 2664488

model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f6f97b3c94548064f0a828787a826e559ce7a21f7bc448d664f020adc1e7ce
+size 5367627

model/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcea6a2e2bbe75b4d76531a5b237eaaaa66d3c9fcbfeb5eb1aaa5792cceb71a
+size 14455

model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132fd8781c473cffddce0bd58abf37281ae52e4b7e41e0deed112a40c16b5ace
+size 1465

model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

model/threshold_global.json

@@ -0,0 +1,3 @@
+{
+    "threshold": 0.55
+}

model/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

model/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_global_step": 300,
+  "best_metric": 0.8175438596491228,
+  "best_model_checkpoint": "outputs/distilbert-lora-multilabel/checkpoint-300",
+  "epoch": 9.375,
+  "eval_steps": 150,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.41905462741851807,
+      "learning_rate": 0.0002817708333333333,
+      "loss": 0.6864,
+      "step": 100
+    },
+    {
+      "epoch": 4.6875,
+      "eval_f1_macro": 0.7462122292280096,
+      "eval_f1_micro": 0.7950963222416813,
+      "eval_loss": 0.47137245535850525,
+      "eval_precision_micro": 0.7773972602739726,
+      "eval_recall_micro": 0.8136200716845878,
+      "eval_runtime": 1.1588,
+      "eval_samples_per_second": 144.974,
+      "eval_steps_per_second": 3.452,
+      "step": 150
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.30065807700157166,
+      "learning_rate": 0.0002296875,
+      "loss": 0.4746,
+      "step": 200
+    },
+    {
+      "epoch": 9.375,
+      "grad_norm": 0.2939732074737549,
+      "learning_rate": 0.00017760416666666665,
+      "loss": 0.4416,
+      "step": 300
+    },
+    {
+      "epoch": 9.375,
+      "eval_f1_macro": 0.7699460773144984,
+      "eval_f1_micro": 0.8175438596491228,
+      "eval_loss": 0.4503212869167328,
+      "eval_precision_micro": 0.8006872852233677,
+      "eval_recall_micro": 0.8351254480286738,
+      "eval_runtime": 1.1768,
+      "eval_samples_per_second": 142.759,
+      "eval_steps_per_second": 3.399,
+      "step": 300
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 640,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 417105484050000.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7718e8e62f303f865483199f8fb75bb58643a47c7c77db781a19c81288e2c45
+size 5841

preprocess_meta.json

@@ -0,0 +1,28 @@
+{
+  "model_name": "distilbert-base-uncased",
+  "max_length": 256,
+  "label2id": {
+    "Business": 0,
+    "Customer Support": 1,
+    "Events & Invitations": 2,
+    "Finance & Bills": 3,
+    "Job Application": 4,
+    "Newsletters": 5,
+    "Personal": 6,
+    "Promotions": 7,
+    "Reminders": 8,
+    "Travel & Bookings": 9
+  },
+  "id2label": {
+    "0": "Business",
+    "1": "Customer Support",
+    "2": "Events & Invitations",
+    "3": "Finance & Bills",
+    "4": "Job Application",
+    "5": "Newsletters",
+    "6": "Personal",
+    "7": "Promotions",
+    "8": "Reminders",
+    "9": "Travel & Bookings"
+  }
+}

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+torch
+transformers>=4.40.0
+peft>=0.10.0
+accelerate