CodeLlama_CPP_FineTuned

Model Card for Model ID

Model Details

Model Description

This model has been fine-tuned using the CodeLlama base, incorporating C++ code sourced from the 'codeparrot/xlcost-text-to-code' dataset. It possesses the capability to generate C++ code based on provided task descriptions.

If you get the error "ValueError: Tokenizer class CodeLlamaTokenizer does not exist or is not currently imported." make sure your Transformer version is 4.33.0 and accelerate>=0.20.3.

• Developed by: [Rudan XIAO]
• Model type: [code generation]
• License: [llama2]
• Finetuned from model [optional]: [codellama/CodeLlama-7b-hf]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [https://github.com/medxiaorudan/CodeGeneration]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

from transformers import AutoTokenizer
import transformers
import torch

model = "medxiaorudan/CodeLlama_CPP_FineTuned" 
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

prompt = """
Use the Task below and write the Response, which is a programming code that can solve the Task.
### Task:
Generate a C++ program that accepts numeric input from the user and maintains a record of previous user inputs with timestamps. Ensure the program sorts the user inputs in ascending order based on the provided numeric input. Enhance the program to display timestamps along with the sorted user inputs.
### Response:
"""
sequences_finetune = pipeline(
    prompt,
    do_sample=True,
    top_k=10,
    temperature=0.1,
    top_p=0.95,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=600,
    add_special_tokens=False
)
for seq in sequences_finetune:
    print(f"Result: {seq['generated_text']}")

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

https://huggingface.co/datasets/codeparrot/xlcost-text-to-code

[More Information Needed]

Training Procedure

The detailed training report is here.

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [bf16] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

I have use the Catch2 unit test framework for generated C++ code snippets correctness verification.

Todo: Use the pass@k metric with the HumanEval-X dataset to verify the performance of the model.

Testing Data, Factors & Metrics

Testing Data

https://huggingface.co/datasets/THUDM/humaneval-x

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

I used 4 NVIDIA A40-48Q GPU server configured with Python 3.10 and Cuda 12.2 to run the code in this article. It ran for about eight hours.

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [NVIDIA A40-48Q GPU]
• Hours used: [8]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.7.1