Upload 7 files

README.md

@@ -1,3 +1,82 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- code
+library_name: peft
+tags:
+- llm2vec
+- mntp
+- decoder-only
+- pre-training
+- codegemma
+---
+
+## 📖 Are Decoder-Only Large Language Models the Silver Bullet for Code Search?
+
+This model is an official artifact from our research paper: **"[Are Decoder-Only Large Language Models the Silver Bullet for Code Search?](https://arxiv.org/abs/2410.22240)"**.
+
+In this work, we conduct a large-scale systematic evaluation of decoder-only Large Language Models for the task of code search and present a set of effective fine-tuning and optimization strategies.
+
+For complete details on all our experiments, to reproduce the full training/evaluation pipeline, or to use other models from the paper, please visit our official GitHub repository:
+
+➡️ **[GitHub: Georgepitt/DecoderLLMs-CodeSearch](https://github.com/Georgepitt/DecoderLLMs-CodeSearch)**
+
+---
+
+## Model Card: CodeGemma-7B - MNTP Pre-trained Model
+
+### 📜 Model Description
+
+This is a PEFT adapter for the **`meta-llama/CodeLlama-7b-Instruct-hf`** model, pre-trained with the **Masked Next Token Prediction (MNTP)** objective from the [llm2vec](https://github.com/McGill-NLP/llm2vec) framework.
+
+**Important Note on its Role**:
+This model is **not intended for direct downstream task evaluation**. Instead, it serves as a crucial **foundational prerequisite** for our supervised fine-tuned (SupCon) models. The MNTP pre-training enables the decoder-only model to learn bidirectional representations, which is an essential step before applying supervised contrastive learning.
+
+### 🚀 How to Use
+
+#### Standalone Use (for Base Embeddings)
+
+You can also use this MNTP model by itself to generate text or code embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel, AutoConfig
+from peft import PeftModel
+from llm2vec import LLM2Vec
+
+base_model_id = "meta-llama/CodeLlama-7b-Instruct-hf"
+mntp_model_id = "SYSUSELab/DCS-CodeLlama-7B-It-MNTP"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+config = AutoConfig.from_pretrained(base_model_id, trust_remote_code=True)
+model = AutoModel.from_pretrained(base_model_id, trust_remote_code=True, config=config, 
+                                  torch_dtype=torch.bfloat16, device_map="auto")
+model = PeftModel.from_pretrained(model, mntp_model_id)
+
+l2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)
+embeddings = l2v.encode(["def hello_world():\n    print('Hello, World!')"])
+print("Embedding from MNTP model:", embeddings.shape)
+```
+
+### ⚙️ Training Methodology
+
+This model was pre-trained using the **MNTP** objective as described in the `llm2vec` paper. If you wish to train your own MNTP model from scratch, please refer to the instructions in the `Fine-tuning/Fine-tuning_method/MNTP/` directory of our GitHub repository.
+
+### 📄 Citation
+
+If you use this model, please cite both our paper and the foundational work of `llm2vec`.
+
+```bibtex
+@article{chen2024decoder,
+  title={Are Decoder-Only Large Language Models the Silver Bullet for Code Search?},
+  author={Chen, Yuxuan and Liu, Mingwei and Ou, Guangsheng and Li, Anji and Dai, Dekun and Wang, Yanlin and Zheng, Zibin},
+  journal={arXiv preprint arXiv:2410.22240},
+  year={2024}
+}
+
+@article{vaishaal2024llm2vec,
+    title={LLM2Vec: Large Language Models Are Good Contextual Text Encoders},
+    author={Vaishaal, Shankar and Bansal, Mohit and Arora, Simran},
+    journal={arXiv preprint arXiv:2404.05961},
+    year={2024}
+}
+```

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlamaBiModel",
+    "parent_library": "llm2vec.models.bidirectional_llama"
+  },
+  "base_model_name_or_path": "meta-llama/CodeLlama-7b-Instruct-hf",
+  "bias": "none",
+  "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_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": [
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cddd13dda40e2ac91c3e671bfd5924c5d488c0ec83a6d2272db97ebda0e8429
+size 80011328

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": "_",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "mask_token": "_",
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}