Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,250 @@
+---
+base_model:
+- BAAI/bge-code-v1
+language:
+- zh
+- en
+tags:
+- bnb-my-repo
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- transformers
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+license: apache-2.0
+---
+# BAAI/bge-code-v1 (Quantized)
+
+## Description
+This model is a quantized version of the original model [`BAAI/bge-code-v1`](https://huggingface.co/BAAI/bge-code-v1). 
+
+It's quantized using the BitsAndBytes library to 4-bit using the [bnb-my-repo](https://huggingface.co/spaces/bnb-community/bnb-my-repo) space.
+
+## Quantization Details
+- **Quantization Type**: int4
+- **bnb_4bit_quant_type**: fp4
+- **bnb_4bit_use_double_quant**: True
+- **bnb_4bit_compute_dtype**: bfloat16
+- **bnb_4bit_quant_storage**: int8
+
+
+
+# 📄 Original Model Information
+
+
+
+<h1 align="center">FlagEmbedding</h1>
+
+For more details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
+
+**BGE-Code-v1** is an LLM-based code embedding model that supports code retrieval, text retrieval, and multilingual retrieval. It primarily demonstrates the following capabilities:
+- Superior Code Retrieval Performance: The model demonstrates exceptional code retrieval capabilities, supporting natural language queries in both English and Chinese, as well as 20 programming languages.
+- Robust Text Retrieval Capabilities: The model maintains strong text retrieval capabilities comparable to text embedding models of similar scale.
+- Extensive Multilingual Support: BGE-Code-v1 offers comprehensive multilingual retrieval capabilities, excelling in languages such as English, Chinese, Japanese, French, and more.
+
+## Usage
+
+### Using FlagEmbedding
+
+```
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
+```
+
+```python
+from FlagEmbedding import FlagLLMModel
+queries = [
+    "Delete the record with ID 4 from the 'Staff' table.", 
+    'Delete all records in the "Livestock" table where age is greater than 5'
+]
+documents = [
+    "DELETE FROM Staff WHERE StaffID = 4;",
+    "DELETE FROM Livestock WHERE age > 5;"
+]
+model = FlagLLMModel('BAAI/bge-code-v1', 
+                     query_instruction_format="<instruct>{}\n<query>{}",
+                     query_instruction_for_retrieval="Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
+                     trust_remote_code=True,
+                     use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+embeddings_1 = model.encode_queries(queries)
+embeddings_2 = model.encode_corpus(documents)
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+```
+
+By default, FlagLLMModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs. You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable.
+
+### Using Sentence Transformers
+
+```python
+from sentence_transformers import SentenceTransformer
+import torch
+
+# Load the model, optionally in float16 precision for faster inference
+model = SentenceTransformer(
+    "BAAI/bge-code-v1",
+    trust_remote_code=True,
+    model_kwargs={"torch_dtype": torch.float16},
+)
+
+# Prepare a prompt given an instruction
+instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
+prompt = f'<instruct>{instruction}\n<query>'
+# Prepare queries and documents
+queries = [
+    "Delete the record with ID 4 from the 'Staff' table.", 
+    'Delete all records in the "Livestock" table where age is greater than 5'
+]
+documents = [
+    "DELETE FROM Staff WHERE StaffID = 4;",
+    "DELETE FROM Livestock WHERE age > 5;"
+]
+
+# Compute the query and document embeddings
+query_embeddings = model.encode(queries, prompt=prompt)
+document_embeddings = model.encode(documents)
+
+# Compute the cosine similarity between the query and document embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+```
+
+### Using HuggingFace Transformers
+
+```python
+import torch
+import torch.nn.functional as F
+
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+
+def last_token_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
+    if left_padding:
+        return last_hidden_states[:, -1]
+    else:
+        sequence_lengths = attention_mask.sum(dim=1) - 1
+        batch_size = last_hidden_states.shape[0]
+        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
+
+
+def get_detailed_instruct(task_description: str, query: str) -> str:
+    return f'<instruct>{task_description}\n<query>{query}'
+
+
+instruction = 'Given a question in text, retrieve SQL queries that are appropriate responses to the question.'
+queries = [
+    "Delete the record with ID 4 from the 'Staff' table.", 
+    'Delete all records in the "Livestock" table where age is greater than 5'
+]
+documents = [
+    "DELETE FROM Staff WHERE StaffID = 4;",
+    "DELETE FROM Livestock WHERE age > 5;"
+]
+input_texts = queries + documents
+
+tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
+model = AutoModel.from_pretrained('BAAI/bge-code-v1', trust_remote_code=True)
+model.eval()
+
+max_length = 4096
+# Tokenize the input texts
+batch_dict = tokenizer(input_texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt', pad_to_multiple_of=8)
+
+with torch.no_grad():
+    outputs = model(**batch_dict)
+    embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
+    
+# normalize embeddings
+embeddings = F.normalize(embeddings, p=2, dim=1)
+scores = (embeddings[:2] @ embeddings[2:].T) * 100
+print(scores.tolist())
+```
+
+## Evaluation
+
+**BGE-Code-v1** achieves state-of-the-art performance on both the CoIR and CodeRAG benchmarks.
+
+- CoIR
+
+|                                 | CodeXEmbed-2B | CodeXEmbed-7B | Voyage-Code-002 | Voyage-Code-003 | BGE-Code-v1 |
+|---------------------------------------|---------------|---------------|-----------------|-----------------|-----------|
+| **Apps**                                  | 76.86         | 85.38         | 26.52           | 93.62           | 98.08     |
+| **CosQA**                                 | 40.47         | 42.47         | 29.79           | 34.45           | 46.72     |
+| **Text2SQL**                              | 78.42         | 78.94         | 69.26           | 62.87           | 64.35     |
+| **CSN**                                   | 87.87         | 89.67         | 81.79           | 89.35           | 89.53     |
+| **CSN-CCR**                               | 97.66         | 97.95         | 73.45           | 90.05           | 98.30     |
+| **CodeTrans-Contest**                     | 90.30         | 94.45         | 72.77           | 94.96           | 94.38     |
+| **CodeTrans-DL**                          | 38.57         | 40.46         | 27.48           | 38.57           | 46.13     |
+| **StackOverFlow-QA**                      | 94.47         | 96.33         | 67.68           | 97.17           | 95.35     |
+| **CodeFeedBack-ST**                       | 86.36         | 87.53         | 65.35           | 90.67           | 90.56     |
+| **CodeFeedBack-MT**                       | 65.51         | 68.83         | 28.74           | 93.58           | 94.38     |
+| **AVG**                                   | **75.65**         | **78.20**         | **56.26**           | **78.53**    | **81.77**     |
+
+- CodedRAG
+
+|                 | HummanEval | MBPP | DS-1000 | ODEX | RepoEval | SWE-bench-Lite | AVG  |
+| --------------- | ---------- | ---- | ------- | ---- | -------- | -------------- | ---- |
+| SFR             | 100.0      | 99.0 | 19.3    | 37.1 | 83.8     | 62.7           | **67.0** |
+| Jina-v2-code    | 100.0      | 97.7 | 26.2    | 19.9 | 90.5     | 58.3           | **65.4** |
+| CodeXEmbed-2B   | 100.0      | 97.4 | 25.4    | 23.9 | 88.7     | 52.4           | **64.6** |
+| Voyage-Code-002 | 100.0      | 99.0 | 33.1    | 26.6 | 94.3     | 29.1           | **63.7** |
+| BGE-Code-v1       | 100.0      | 99.2 | 40.9    | 36.1 | 93.1     | 67.4           | **72.8** |
+
+### Instructions for Evaluation
+
+```python
+{
+    "Apps": "Given a code contest problem description, retrieve relevant code that can help solve the problem.",
+    "CosQA": "Given a web search query, retrieve relevant code that can help answer the query.",
+    "Text2SQL": "Given a question in text, retrieve SQL queries that are appropriate responses to the question.",
+    "CSN": "Given a piece of code, retrieve the document string that summarizes the code.",
+    "CSN-CCR": "Given a piece of code segment, retrieve the code segment that is the latter part of the code.",
+    "CodeTrans-DL": "Given a piece of code, retrieve code that is semantically equivalent to the input code.",
+    "CodeTrans-Contest": "Given a piece of Python code, retrieve C++ code that is semantically equivalent to the input code.",
+    "StackOverFlow-QA": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "CodeFeedBack-ST": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "CodeFeedBack-MT": "Given a multi-turn conversation history that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "HummanEval": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "MBPP": "Given a textual explanation of code functionality, retrieve the corresponding code implementation.",
+    "DS-1000": "Given a question that consists of a mix of text and code snippets, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "ODEX": "Given a question, retrieve relevant answers that also consist of a mix of text and code snippets, and can help answer the question.",
+    "RepoEval": "Given a piece of code segment, retrieve the code segment that is the latter part of the code.",
+    "SWE-bench-Lite": "Given a code snippet containing a bug and a natural language description of the bug or error, retrieve code snippets that demonstrate solutions or fixes for similar bugs or errors (the desired documents)."
+}
+```
+
+## Citation
+
+If you find this repository useful, please consider giving a star :star: and citation
+
+```
+@article{bge-llm,
+  title={Making text embedders few-shot learners},
+  author={Li, Chaofan and Qin, MingHao and Xiao, Shitao and Chen, Jianlyu and Luo, Kun and Shao, Yingxia and Lian, Defu and Liu, Zheng},
+  journal={arXiv preprint arXiv:2409.15700},
+  year={2024}
+}
+
+@misc{bge-m3,
+      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
+      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
+      year={2024},
+      eprint={2402.03216},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+
+@misc{bge_embedding,
+      title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, 
+      author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
+      year={2023},
+      eprint={2309.07597},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

added_tokens.json

@@ -0,0 +1,26 @@
+{
+  "</tool_call>": 151658,
+  "<instruct>": 151665,
+  "<query>": 151666,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "BAAI/bge-code-v1",
+  "architectures": [
+    "Qwen2Model"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "int8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151667
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33d70912d75fb23aa0d9ce3656fc9a9b93d59e42647c9bf86b8fb4ffabe9419
+size 1608708594

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<instruct>",
+    "<query>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56524092f5d0676e63537511b535e73e7580a7efe440247ef3fa43d019a0af0
+size 11422261

tokenizer_config.json

@@ -0,0 +1,220 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<instruct>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<instruct>",
+    "<query>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "BAAI/bge-code-v1--tokenization_qwen.Qwen2Tokenizer",
+      null
+    ]
+  },
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 256,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}