Instructions to use AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0")
model = AutoModelForCausalLM.from_pretrained("AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

SGLang

How to use AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 with Docker Model Runner:
```
docker model run hf.co/AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

Downloads last month: 2

Model tree for AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

Quantizations

1 model

Dataset used to train AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0

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

ML4SE23

Collection

Collection of models for the course. Naming convention: ML4SE23_G{group_number}_{model_name} • 27 items • Updated Nov 8, 2023 • 2