Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+spiece.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,10 @@
+This model is a T5-base reranker fine-tuned on the MS MARCO passage dataset for 100k steps (or 10 epochs).
+
+For better zero-shot performance (i.e., inference on other datasets), we recommend using `castorini/monot5-base-msmarco-10k`.
+
+For more details on how to use it, check the following links:
+- [A simple reranking example](https://github.com/castorini/pygaggle#a-simple-reranking-example)
+- [Rerank MS MARCO passages](https://github.com/castorini/pygaggle/blob/master/docs/experiments-msmarco-passage-subset.md)
+- [Rerank Robust04 documents](https://github.com/castorini/pygaggle/blob/master/docs/experiments-robust04-monot5-gpu.md)
+
+Paper describing the model: [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://www.aclweb.org/anthology/2020.findings-emnlp.63/)

config.json

@@ -0,0 +1,81 @@
+{
+  "_num_labels": 2,
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "do_sample": false,
+  "dropout_rate": 0.1,
+  "early_stopping": false,
+  "eos_token_id": 1,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "model_type": "t5",
+  "n_positions": 512,
+  "no_repeat_ngram_size": 0,
+  "num_beams": 1,
+  "num_heads": 12,
+  "num_layers": 12,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": 0,
+  "prefix": null,
+  "pruned_heads": {},
+  "relative_attention_num_buckets": 32,
+  "repetition_penalty": 1.0,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "use_bfloat16": false,
+  "vocab_size": 32128
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd58affd5786e328e6a1afadc39cc33d63e2a8f111bbbccc69212395c2f38592
+size 891625348

handler.py

@@ -0,0 +1,103 @@
+"""
+Custom handler for MonoT5 reranking on HuggingFace Inference Endpoints.
+
+Returns relevance probability scores for query-document pairs.
+"""
+
+import math
+from typing import Any, Dict, List
+
+import torch
+from transformers import T5ForConditionalGeneration, T5Tokenizer
+
+
+class EndpointHandler:
+    """Handler for MonoT5 relevance scoring."""
+    
+    def __init__(self, path: str = ""):
+        """Initialize the model and tokenizer."""
+        self.tokenizer = T5Tokenizer.from_pretrained(path)
+        self.model = T5ForConditionalGeneration.from_pretrained(path)
+        self.model.eval()
+        
+        # Move to GPU if available
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model = self.model.to(self.device)
+        
+        # Get token IDs for "true" and "false"
+        self.true_id = self.tokenizer.encode("true", add_special_tokens=False)[0]
+        self.false_id = self.tokenizer.encode("false", add_special_tokens=False)[0]
+        
+        print(f"MonoT5 loaded on {self.device}")
+    
+    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """
+        Process inference requests.
+        
+        Accepts either:
+        - {"inputs": "Query: ... Document: ... Relevant:"} - single input
+        - {"inputs": ["Query: ... Document: ... Relevant:", ...]} - batch
+        - {"query": "...", "documents": ["...", ...]} - structured input
+        
+        Returns:
+        - List of {"score": float, "label": "true"/"false"} dicts
+        """
+        inputs = data.get("inputs", data)
+        
+        # Handle structured input format
+        if "query" in data and "documents" in data:
+            query = data["query"]
+            documents = data["documents"]
+            inputs = [
+                f"Query: {query} Document: {doc} Relevant:"
+                for doc in documents
+            ]
+        
+        # Ensure inputs is a list
+        if isinstance(inputs, str):
+            inputs = [inputs]
+        
+        # Score all inputs
+        results = []
+        for input_text in inputs:
+            score = self._score_single(input_text)
+            results.append({
+                "score": score,
+                "label": "true" if score > 0.5 else "false"
+            })
+        
+        return results
+    
+    def _score_single(self, input_text: str) -> float:
+        """Score a single query-document pair."""
+        # Tokenize
+        inputs = self.tokenizer(
+            input_text,
+            return_tensors="pt",
+            max_length=512,
+            truncation=True,
+            padding=True
+        ).to(self.device)
+        
+        # Get logits for first generated token
+        with torch.no_grad():
+            decoder_input_ids = torch.tensor(
+                [[self.tokenizer.pad_token_id]], 
+                device=self.device
+            )
+            outputs = self.model(
+                **inputs,
+                decoder_input_ids=decoder_input_ids
+            )
+            logits = outputs.logits[0, -1, :]
+        
+        # Get probabilities for true/false tokens
+        true_logit = logits[self.true_id].item()
+        false_logit = logits[self.false_id].item()
+        
+        # Softmax over true/false
+        max_logit = max(true_logit, false_logit)
+        true_prob = math.exp(true_logit - max_logit)
+        false_prob = math.exp(false_logit - max_logit)
+        
+        return true_prob / (true_prob + false_prob)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64467f69fc891a29b35b386b7d66e4a3cdb2285588dcc85b56c396eb3a31b398
+size 891691413

requirements.txt

@@ -0,0 +1,3 @@
+transformers>=4.30.0
+torch>=2.0.0
+sentencepiece

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base"}