AISE-TUDelft / ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

huggingface.co
Total runs: 27
24-hour runs: 6
7-day runs: 4
30-day runs: 7
Model's Last Updated: November 05 2023
text-generation

Introduction of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

Model Details of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

IN4334 ML4SE

Group1 WizardCoder

This model is the result of the fine-tunign of the WizardCoder-1B-V1.0 model using Structured Chain-of-Though (S-CoT) enhanced instructions. S-CoT is used to enhance a sample of about 1200 entries from the Evol-Instruct 80k dataset. The resulting dataset is then used for the training task. The current WizardCoder model and the new S-CoT fine-tuned one are compared on both versions of HumanEval and MBPP (S-CoT enhanced and not) on the pass@1 metric. The S-CoT enhancement of the evaluation datasets allows to study its effect when used just as a prompting technique, independently of the S-CoT fine-tuning of the model.

Fine-tuning Details
Hyperparameter WizardCoder-1B-V1.0
Batch size 16
Learning rate 2e-5
Epochs 3
Max length 2048
Warmup step 30
LR scheduler cosine
Dataset ML4SE23_G1_EvolInstruct-SCoT-1k

The hardware consisted on a GPU instance rented from DataCrunch with the following specifications:

NVidia RTX A6000 48GB 1A6000.10V
2 GPUs
48GB VRAM per GPU
60 GB RAM
10 CPUs
100GB SSD Storage
Ubuntu 20.04
CUDA 11.6
Results

Results of pass@1(%) on HumanEval and MBPP compared to HumanEval-SCoT and MBPP-SCoT using WizardCoder-1B, WizardCoder-SCoT-1B and WizardCoder-15B.

Dataset WizardCoder-1B-V1.0 WizardCoder-SCoT-1B-V1.0 WizardCoder-15B-V1.0
HumanEval 23.78 17.68 57.3
HumanEval-SCoT 44.51 27.44 57.3
MBPP 23.4 19.4 51.8
MBPP-SCoT 40 28 45.6

Runs of AISE-TUDelft ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 on huggingface.co

27
Total runs
6
24-hour runs
3
3-day runs
4
7-day runs
7
30-day runs

More Information About ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co Model

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co is an AI model on huggingface.co that provides ML4SE23_G1_WizardCoder-SCoT-1B-V1.0's model effect (), which can be used instantly with this AISE-TUDelft ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 model. huggingface.co supports a free trial of the ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 model, and also provides paid use of the ML4SE23_G1_WizardCoder-SCoT-1B-V1.0. Support call ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 model through api, including Node.js, Python, http.

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co Url

https://huggingface.co/AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

AISE-TUDelft ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 online free

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co is an online trial and call api platform, which integrates ML4SE23_G1_WizardCoder-SCoT-1B-V1.0's modeling effects, including api services, and provides a free online trial of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0, you can try ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 online for free by clicking the link below.

AISE-TUDelft ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 online free url in huggingface.co:

https://huggingface.co/AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 install

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 is an open source model from GitHub that offers a free installation service, and any user can find ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 on GitHub to install. At the same time, huggingface.co provides the effect of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 install, users can directly use ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 install url in huggingface.co:

https://huggingface.co/AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

Url of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co Url

Provider of ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 huggingface.co

AISE-TUDelft
ORGANIZATIONS

Other API from AISE-TUDelft