Instructions to use semcoder/semcoder_1030 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use semcoder/semcoder_1030 with Transformers:

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

pipe = pipeline("text-generation", model="semcoder/semcoder_1030")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("semcoder/semcoder_1030")
model = AutoModelForCausalLM.from_pretrained("semcoder/semcoder_1030")
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 semcoder/semcoder_1030 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "semcoder/semcoder_1030"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "semcoder/semcoder_1030",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/semcoder/semcoder_1030

SGLang

How to use semcoder/semcoder_1030 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 "semcoder/semcoder_1030" \
    --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": "semcoder/semcoder_1030",
		"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 "semcoder/semcoder_1030" \
        --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": "semcoder/semcoder_1030",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use semcoder/semcoder_1030 with Docker Model Runner:
```
docker model run hf.co/semcoder/semcoder_1030
```

semcoder_1030 / README.md

Robin Ding

update README

ff39b20 over 1 year ago

preview code

raw

history blame contribute delete

2.87 kB

metadata

license: other
library_name: transformers
license_name: deepseek
license_link: https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL
pipeline_tag: text-generation

🤔 SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

Refer to our GitHub repo ARiSE-Lab/SemCoder for detailed introduction to SemCoder!

Model Details

Use the code below to get started with the model. Make sure you installed the transformers library.

from transformers import pipeline
import torch

generator = pipeline(
  model="semcoder/semcoder_1030",
  task="text-generation",
  torch_dtype=torch.float16,
  device_map="auto",
)

# Generate Code

CODEGEN_REQUEST = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable <Code> according to <NL_Description>

<NL_Description>
{desc}

<Code>
"""
desc = """You are tasked with implementing a Python class that simulates a simple version of a "To-Do List" application. The class should have the following functionalities:
1. Add a new task to the to-do list.
2. Mark a task as completed.
3. Display all tasks in the to-do list.
4. Display only the incomplete tasks in the to-do list.
"""

prompt = CODEGEN_REQUEST.format(desc=desc)
result = generator(prompt, max_length=2048, num_return_sequences=1, temperature=0.0)
code = result[0]["generated_text"].split("```python")[1].split("```")[0]
print(code)

# Understand Code with Monologues

FWD_MNL_REQUEST = """Simulate the Execution: You are given a Python function and an assertion containing a function input. Complete the assertion containing the execution output corresponding to the given input in [ANSWER] and [/ANSWER] tags.
{code}
"""

tests = """
todo_list = ToDoList()
todo_list.add_task("Buy groceries")
todo_list.add_task("Complete assignment")
todo_list.mark_completed("Buy groceries")
assert todo_list.tasks == ???
"""
code += tests
prompt = FWD_MNL_REQUEST.format(code=code)
result = generator(prompt, max_length=2048, num_return_sequences=1, temperature=0.0)
print(result[0]["generated_text"])

Citation

@article{ding2024semcoder,
  title={SemCoder: Training Code Language Models with Comprehensive Semantics},
  author={Yangruibo Ding and Jinjun Peng and Marcus J. Min and Gail Kaiser and Junfeng Yang and Baishakhi Ray},
  journal={arXiv preprint arXiv:2406.01006},
  year={2024}
}

Important Note

SemCoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's terms of use when using the models and the datasets. SemCoder will not compete with OpenAI's commercial products.