license: mit
library_name: transformers
base_model:
- Salesforce/codet5-base
pipeline_tag: text-generation
tags:
- code
- mathematics
- theorem-proving
Model Card for CodeFuse-DeepSeek-33B
Github: https://github.com/trishullab/proof-wala
Model Description
CodeFuse-DeepSeek-33B is a 33B Code-LLM finetuned by QLoRA on multiple code-related tasks on the base model DeepSeek-Coder-33B.
News and Updates
🔥🔥🔥 2024-01-12 CodeFuse-DeepSeek-33B has been released, achieving a pass@1 (greedy decoding) score of 78.65% on HumanEval.
🔥🔥🔥 2024-01-12 CodeFuse-Mixtral-8x7B has been released, achieving a pass@1 (greedy decoding) score of 56.1% on HumanEval, which is a 15% increase compared to Mixtral-8x7b's 40%.
🔥🔥 2023-11-10 CodeFuse-CodeGeeX2-6B has been released, achieving a pass@1 (greedy decoding) score of 45.12% on HumanEval, which is a 9.22% increase compared to CodeGeeX2 35.9%.
🔥🔥 2023-10-20 CodeFuse-QWen-14B technical documentation has been released. For those interested, please refer to the CodeFuse article on our WeChat official account via the provided link.(https://mp.weixin.qq.com/s/PCQPkvbvfxSPzsqjOILCDw)
🔥🔥 2023-10-16 CodeFuse-QWen-14B has been released, achieving a pass@1 (greedy decoding) score of 48.78% on HumanEval, which is a 16% increase compared to Qwen-14b's 32.3%.
🔥🔥 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
🔥🔥 2023-09-26 We are pleased to announce the release of the 4-bit quantized version of CodeFuse-CodeLlama-34B. Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
🔥🔥 2023-09-11 CodeFuse-CodeLlama-34B has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
Code Community
Homepage: 🏡 https://github.com/codefuse-ai (Please give us your support with a Star🌟 + Fork🚀 + Watch👀)
If you wish to fine-tune the model yourself, you can visit ✨MFTCoder✨✨
If you wish to see a demo of the model, you can visit ✨CodeFuse Demo✨✨
Performance
Code
| Model | HumanEval(pass@1) | Date |
|---|---|---|
| CodeFuse-DeepSeek-33B | 78.65% | 2024.01 |
| CodeFuse-Mixtral-8x7B | 56.10% | 2024.01 |
| CodeFuse-CodeLlama-34B | 74.4% | 2023.9 |
| CodeFuse-CodeLlama-34B-4bits | 73.8% | 2023.9 |
| CodeFuse-StarCoder-15B | 54.9% | 2023.9 |
| CodeFuse-QWen-14B | 48.78% | 2023.10 |
| CodeFuse-CodeGeeX2-6B | 45.12% | 2023.11 |
| WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
| GPT-4(zero-shot) | 67.0% | 2023.3 |
| PanGu-Coder2 15B | 61.6% | 2023.8 |
| CodeLlama-34b-Python | 53.7% | 2023.8 |
| CodeLlama-34b | 48.8% | 2023.8 |
| GPT-3.5(zero-shot) | 48.1% | 2022.11 |
| OctoCoder | 46.2% | 2023.8 |
| StarCoder-15B | 33.6% | 2023.5 |
| Qwen-14b | 32.3% | 2023.10 |
NLP
Requirements
- python>=3.8
- pytorch>=2.0.0
- transformers>=4.33.2
- Sentencepiece
- CUDA 11.4
Inference String Format
The inference string is a concatenated string formed by combining conversation data(system, human and bot contents) in the training data format. It is used as input during the inference process. Here are examples of prompts used to request the model:
Multi-Round with System Prompt:
"""
<s>system
System instruction
<s>human
Human 1st round input
<s>bot
Bot 1st round output<｜end of sentence｜>
<s>human
Human 2nd round input
<s>bot
Bot 2nd round output<｜end of sentence｜>
...
...
...
<s>human
Human nth round input
<s>bot
"""
Single-Round without System Prompt:
"""
<s>human
User prompt...
<s>bot
"""
In this format, the system section is optional and the conversation can be either single-turn or multi-turn. When applying inference, you always make your input string end with "<s>bot" to ask the model generating answers.
For example, the format used to infer HumanEval is like the following:
<s>human
# language: Python
from typing import List
def separate_paren_groups(paren_string: str) -> List[str]:
""" Input to this function is a string containing multiple groups of nested parentheses. Your goal is to
separate those group into separate strings and return the list of those.
Separate groups are balanced (each open brace is properly closed) and not nested within each other
Ignore any spaces in the input string.
>>> separate_paren_groups('( ) (( )) (( )( ))')
['()', '(())', '(()())']
"""
<s>bot
Specifically, we also used the CodeGeeX series model's programming language distinction tag (e.g., for Python language, we use "# language: Python").
Quickstart
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
model_dir = "codefuse-ai/CodeFuse-DeepSeek-33B"
def load_model_tokenizer(model_path):
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
tokenizer.eos_token = "<｜end of sentence｜>"
tokenizer.pad_token = "<｜end of sentence｜>"
tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids(tokenizer.eos_token)
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids(tokenizer.pad_token)
tokenizer.padding_side = "left"
model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto',torch_dtype=torch.bfloat16, trust_remote_code=True)
return model, tokenizer
HUMAN_ROLE_START_TAG = "<s>human\n"
BOT_ROLE_START_TAG = "<s>bot\n"
text_list = [f'{HUMAN_ROLE_START_TAG}Please write a quicksort program\n#Python\n{BOT_ROLE_START_TAG}']
model, tokenizer = load_model_tokenizer(model_dir)
inputs = tokenizer(text_list, return_tensors='pt', padding=True, add_special_tokens=False).to('cuda')
input_ids = inputs["input_ids"]
attention_mask = inputs["attention_mask"]
generation_config = GenerationConfig(
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
temperature=0.2,
max_new_tokens=512,
num_return_sequences=1,
num_beams=1,
top_p=0.95,
do_sample=False
)
outputs = model.generate(
inputs= input_ids,
attention_mask=attention_mask,
**generation_config.to_dict()
)
gen_text = tokenizer.batch_decode(outputs[:, input_ids.shape[1]:], skip_special_tokens=True)
print(gen_text[0])