Model Card for CodeFuse-StarCoder-15B

[中文] [English]

Model Description

CodeFuse-StarCoder-15B is a 15B Code-LLM finetuned by QLoRA of multiple code tasks（600k instrunctions/answers）on the base model StarCoder. CodeFuse-StarCoder-15B is a smaller Code-LLM than our CodeFuse-CodeLlama-34B and using MQA, thus faster on inference. The context length of finetuning is 4K.

News and Updates

        ? 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval.

??? 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-CodeLlama34B has achived 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 deploy the model yourself, you can visit ✨FasterTransformer4CodeFuse✨✨

• If you wish to see a demo of the model, you can visit ✨CodeFuse Demo✨✨

Performance

Requirements

• python>=3.8
• pytorch>=2.0.0
• transformers==4.32.0
• 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 is an example format of the concatenated string:

"""
<|role_start|>system<|role_end|>System instruction
<|role_start|>human<|role_end|>Human 1st round input
<|role_start|>bot<|role_end|>Bot 1st round output</s>
<|role_start|>human<|role_end|>Human 2nd round input
<|role_start|>bot<|role_end|>Bot 2nd round output</s>
...
...
...
<|role_start|>human<|role_end|>Human nth round input
<|role_start|>bot<|role_end|>{Bot output to be genreated}</s>
"""

When applying inference, you always make your input string end with "<|rolestart|>bot<|roleend|>" to ask the model generating answers.

Quickstart

 git clone https://www.modelscope.cn/codefuse-ai/CodeFuse-StarCoder-15B.git

pip install -r requirements.txt

import torch
from modelscope import (
    AutoTokenizer, 
    AutoModelForCausalLM,
    snapshot_download
)
model_dir = snapshot_download('codefuse-ai/CodeFuse-StarCoder-15B',revision = 'v1.0.0')
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True, use_fast=False, legacy=False)
tokenizer.padding_side = "left"
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<fim_pad>")
tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("<|endoftext|>")
tokenizer.pad_token = "<fim_pad>"
tokenizer.eos_token = "<|endoftext|>"
# try 4bit loading if cuda memory not enough
model = AutoModelForCausalLM.from_pretrained(model_dir,
                                             trust_remote_code=True,
                                             load_in_4bit=False,
                                             device_map="auto",
                                             torch_dtype=torch.bfloat16)
model.eval()

HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"

text = f"{HUMAN_ROLE_START_TAG}write a python function of quick sort.{BOT_ROLE_START_TAG}" 
inputs = tokenizer(text, return_tensors='pt', padding=True, add_special_tokens=False).to("cuda")
outputs = model.generate(
        inputs=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_new_tokens=512,
        top_p=0.95,
        temperature=0.1,
        do_sample=True,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id
    )
gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(gen_text)

MD5

We notice that the file may be corrupted during transfer process. Please check MD5 value before use.

模型简介

CodeFuse-StarCoder-15B 是一个通过QLoRA对基座模型StarCoder进行多代码任务微调的代码大模型。模型微调采用了4k上下文。该模型相比于我们近期开源的 CodeFuse-CodeLlama-34B ，模型小一些，并采用了MQA技术，推理速度比较快。

新闻

        ? 2023-09-27开源了CodeFuse-StarCoder-15B模型，在HumanEval pass@1(greedy decoding)上可以达到54.9%

??? 2023-09-26 CodeFuse-CodeLlama-34B 4bits量化版本发布，量化后模型在HumanEval pass@1指标为73.8% (贪婪解码)。

??? 2023-09-11 CodeFuse-CodeLlama-34B发布，HumanEval pass@1指标达到74.4% (贪婪解码), 为当前开源SOTA。

代码社区

大本营： ? https://github.com/codefuse-ai （请支持我们的项目Star? + Fork? + Watch?）

• 如果您想自己微调该模型，可以访问 ✨MFTCoder✨✨

• 如果您想自己部署该模型，可以访问 ✨FasterTransformer4CodeFuse✨✨

• 如果您想观看该模型示例，可以访问 ✨CodeFuse Demo✨✨

评测表现(代码)

Requirements

• python>=3.8
• pytorch>=2.0.0
• transformers==4.32.0
• Sentencepiece
• CUDA 11.4
  

推理数据格式

推理数据为模型在训练数据格式下拼接的字符串形式，它也是推理时输入prompt拼接的方式：

"""
<|role_start|>system<|role_end|>这是System指令
<|role_start|>human<|role_end|>这是第1轮用户输入的问题
<|role_start|>bot<|role_end|>这是第1轮模型生成的内容</s>
<|role_start|>human<|role_end|>这是第2轮用户输入的问题
<|role_start|>bot<|role_end|>这是第2轮模型生成的内容</s>
...
...
...
<|role_start|>human<|role_end|>这是第n轮用户输入的问题
<|role_start|>bot<|role_end|>{模型现在要生成的内容}</s>
"""

推理时，请确保拼接的prompt字符串以"<|rolestart|>bot<|roleend|>"结尾，引导模型生成回答。

快速使用

 git clone https://www.modelscope.cn/codefuse-ai/CodeFuse-StarCoder-15B.git

pip install -r requirements.txt

import torch
from modelscope import (
    AutoTokenizer, 
    AutoModelForCausalLM,
    snapshot_download
)
model_dir = snapshot_download('codefuse-ai/CodeFuse-StarCoder-15B',revision = 'v1.0.0')
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True, use_fast=False, legacy=False)
tokenizer.padding_side = "left"
tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids("<fim_pad>")
tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids("<|endoftext|>")
tokenizer.pad_token = "<fim_pad>"
tokenizer.eos_token = "<|endoftext|>"
# try 4bit loading if cuda memory not enough
model = AutoModelForCausalLM.from_pretrained(model_dir,
                                             trust_remote_code=True,
                                             load_in_4bit=False,
                                             device_map="auto",
                                             torch_dtype=torch.bfloat16)
model.eval()

HUMAN_ROLE_START_TAG = "<|role_start|>human<|role_end|>"
BOT_ROLE_START_TAG = "<|role_start|>bot<|role_end|>"

text = f"{HUMAN_ROLE_START_TAG}write a python function of quick sort.{BOT_ROLE_START_TAG}" 
inputs = tokenizer(text, return_tensors='pt', padding=True, add_special_tokens=False).to("cuda")
outputs = model.generate(
        inputs=inputs["input_ids"],
        attention_mask=inputs["attention_mask"],
        max_new_tokens=512,
        top_p=0.95,
        temperature=0.1,
        do_sample=True,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id
    )
gen_text = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(gen_text)

MD5

我们发现模型文件可能会在传输过程中损坏，使用前请检查文件MD5值。