Instructions to use ed001/datascience-coder-6.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ed001/datascience-coder-6.7b with Transformers:

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

pipe = pipeline("text-generation", model="ed001/datascience-coder-6.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ed001/datascience-coder-6.7b")
model = AutoModelForCausalLM.from_pretrained("ed001/datascience-coder-6.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ed001/datascience-coder-6.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ed001/datascience-coder-6.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ed001/datascience-coder-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ed001/datascience-coder-6.7b

SGLang

How to use ed001/datascience-coder-6.7b 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 "ed001/datascience-coder-6.7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ed001/datascience-coder-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ed001/datascience-coder-6.7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ed001/datascience-coder-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ed001/datascience-coder-6.7b with Docker Model Runner:
```
docker model run hf.co/ed001/datascience-coder-6.7b
```

The Data Science Coder

Data Science coder is a group of fine tuned models designed to help with coding for data science applications. It comes in 2 variants: 1.3b and 6.7b. Models are fine tuned from DeepSeek Coder instruct versions. Fine tuning was performed on the ed001/ds-coder-instruct-v1 dataset which is constructed by filtering publicly available datasets on HuggingFace.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

def build_instruction_prompt(instruction):
    return '''
    You are the Data Science Coder, a helpful AI assistant created by a man named Ed.
    You help people with data science coding and you answer questions about data science in a helpful manner.
    ### Instruction:
    {}
    ### Response:
    '''.format(instruction.strip()).lstrip()

tokenizer = AutoTokenizer.from_pretrained("ed001/datascience-coder-6.7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ed001/datascience-coder-6.7b", trust_remote_code=True).cuda()
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=1024, top_p=0.95)
result = pipe(build_instruction_prompt("Perform EDA on the Iris dataset"))
print(result[0]['generated_text'])

Training Details

lora_r: 16
lora_alpha: 8
lora_dropout: 0.05
target_modules: q, k, v, o, gate_proj, down_proj, up_proj, lm_head
weight_decay: 0
optmizer: paged_adamw_32bit
lr: 1e-4
lr_scheduler: cosine
max_seq_len: 4096
batch_size: 4
max_grad_norm: 0.5
warmup_ratio: 0.05
num_epochs: 1

The model was trained on the python susbet of the ds-coder-instruct dataset.

Samples

Contact

GitHub: Ea0011

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	41.99
AI2 Reasoning Challenge (25-Shot)	34.64
HellaSwag (10-Shot)	53.83
MMLU (5-Shot)	37.96
TruthfulQA (0-shot)	44.82
Winogrande (5-shot)	55.72
GSM8k (5-shot)	24.94

Downloads last month: 1,033

Safetensors

Model size

7B params

Tensor type

F32

F16

Dataset used to train ed001/datascience-coder-6.7b

Collection including ed001/datascience-coder-6.7b

data science code generation

Collection

This is a collection of datasets and models used to generate data science related code • 6 items • Updated Apr 10, 2024 • 1

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

34.640
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

53.830
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

37.960
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.820
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

55.720
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

24.940