initial commit

.gitattributes

@@ -0,0 +1 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<mask>": 49152,
+  "<pad>": 49153
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Partha117/blaze",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeSageModel"
+  ],
+  "attention_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "codesage/codesage-small--config_codesage.CodeSageConfig",
+    "AutoModel": "codesage/codesage-small--modeling_codesage.CodeSageModel",
+    "AutoModelForMaskedLM": "codesage/codesage-small--modeling_codesage.CodeSageForMaskedLM",
+    "AutoModelForSequenceClassification": "codesage/codesage-small--modeling_codesage.CodeSageForSequenceClassification"
+  },
+  "bos_token_id": 0,
+  "embedding_dropout_prob": 0.1,
+  "eos_token_id": 0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "codesage",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "pad_token_id": 49153,
+  "position_embedding_type": "absolute",
+  "residual_dropout_prob": 0.1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 49154
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15363f2a8398bceeecb427041e20560abfae5dda0ebef83a52162a417575b920
+size 512047808

readme.md

@@ -0,0 +1,50 @@
+# Blaze (Finetuned Variant)
+
+This model is a finetuned version of the **BLAZE** model described in the paper:
+
+**_BLAZE: Cross‑Language and Cross‑Project Bug Localization via Dynamic Chunking and Hard Example Learning_**  
+DOI: [10.5281/zenodo.15122980](https://doi.org/10.5281/zenodo.15122980) :contentReference[oaicite:1]{index=1}
+
+---
+
+## 📘 What’s Inside
+
+A Transformer-based bug localization model fine-tuned on additional cross-project datasets to enhance its ability to pinpoint bugs in unseen codebases.
+
+---
+
+## 🧪 Fine-tuning Details
+
+- **Starting point:** Pretrained Blaze model from Zenodo.
+- **Enhancements:** Further trained on a curated dataset using dynamic chunking and hard-negative sampling — all detailed in the original manuscript and accompanying code release.
+
+---
+
+## 🔍 Intended Usage
+
+- **Primary task:** Automatic identification of buggy code segments across languages and projects.
+- **How to use:** Load the model and feed it code snippets to receive localized bug predictions.
+
+---
+
+## 📄 Citation
+
+If you use this model, please cite:
+
+> _BLAZE: Cross‑Language and Cross‑Project Bug Localization via Dynamic Chunking and Hard Example Learning_, available at DOI: 10.5281/zenodo.15122980 :contentReference[oaicite:2]{index=2}
+
+---
+
+## 📁 Contents of This Repo
+
+- `config.json`  
+- `pytorch_model.bin` (or `tf_model.h5`)  
+- `tokenizer.json` (if applicable)  
+- `README.md`
+
+---
+
+## 🛠️ Setup
+
+```bash
+pip install transformers huggingface_hub

special_tokens_map.json

@@ -0,0 +1,58 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "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
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}