Instructions to use HelpingAI/Cipher-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HelpingAI/Cipher-20B with Transformers:

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

pipe = pipeline("text-generation", model="HelpingAI/Cipher-20B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HelpingAI/Cipher-20B")
model = AutoModelForCausalLM.from_pretrained("HelpingAI/Cipher-20B", device_map="auto")
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 Settings

vLLM

How to use HelpingAI/Cipher-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HelpingAI/Cipher-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HelpingAI/Cipher-20B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HelpingAI/Cipher-20B

SGLang

How to use HelpingAI/Cipher-20B 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 "HelpingAI/Cipher-20B" \
    --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": "HelpingAI/Cipher-20B",
		"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 "HelpingAI/Cipher-20B" \
        --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": "HelpingAI/Cipher-20B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HelpingAI/Cipher-20B with Docker Model Runner:
```
docker model run hf.co/HelpingAI/Cipher-20B
```

Cipher-20B / README.md

Abhaykoul

Upload folder using huggingface_hub

69e935c verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

4.59 kB

	---
	license: other
	license_name: helpingai
	license_link: https://helpingai.co/license
	pipeline_tag: text-generation
	language:
	- en
	tags:
	- HelpingAI
	- Cipher
	- Code Generation
	- Programming
	- AI Assistant
	library_name: transformers
	---

	<div align="center">
	💻 <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Cipher-20B</span>
	</div>

	<div align="center" style="display: flex; justify-content: center; gap: 4px;">
	<a href="https://github.com/HelpingAI"><img src="https://img.shields.io/badge/GitHub-Organization-blue.svg" alt="GitHub Organization"></a>
	<a href="https://huggingface.co/HelpingAI"><img src="https://img.shields.io/badge/🤗%20Hugging%20Face-Organization-yellow" alt="Hugging Face"></a>
	<a href="https://helpingai.co/license"><img src="https://img.shields.io/badge/License-HelpingAI-green.svg" alt="Model License"></a>
	<a href="https://github.com/HelpingAI/community/discussions"><img src="https://img.shields.io/badge/Join-Community%20Discussion-blue?style=for-the-badge&logo=github" alt="Join Community Discussion"></a>
	</div>

	<div align="center">
	[📜 License](https://helpingai.co/license) \| [🌐 Website](https://helpingai.co)
	</div>

	<div align="center" style="display: flex; justify-content: center; gap: 4px;">
	<img src="https://img.shields.io/badge/Model%20Size-20B-ff6347" alt="Model Size">
	<img src="https://img.shields.io/badge/Task-Code%20Generation-blue" alt="Task">
	<img src="https://img.shields.io/badge/Deployment-Efficient%20&%20Fast-yellow" alt="Deployment Speed">
	</div>

	## 🌟 <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">About Cipher-20B</span>

	Cipher-20B is a 20 billion parameter causal language model designed for code generation.

	### 💻 <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Implementation</span>

	### <span style="color: #FF6347;">Using Transformers</span>

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	# Load Cipher-20B
	model = AutoModelForCausalLM.from_pretrained("HelpingAI/Cipher-20B")
	tokenizer = AutoTokenizer.from_pretrained("HelpingAI/Cipher-20B")

	# Example usage
	code_task = [
	{"role": "system", "content": "You are Cipher"},
	{"role": "user", "content": "Write a Python function to calculate the Fibonacci sequence."}
	]

	inputs = tokenizer.apply_chat_template(
	code_task,
	add_generation_prompt=True,
	return_tensors="pt"
	)

	outputs = model.generate(
	inputs,
	max_new_tokens=256,
	temperature=0.7,
	top_p=0.9,
	)

	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## ⚙️ <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Training Details</span>

	### <span style="color: #FF6347;">Training Data</span>
	* Trained on a large dataset of code, programming tasks, and technical documentation.
	* Fine-tuned for multiple programming languages like Python, JavaScript, and C++.

	### <span style="color: #FFD700;">Capabilities</span>
	* Generates code in multiple languages.
	* Detects and corrects common coding errors.
	* Provides clear explanations of code.

	## ⚠️ <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Limitations</span>

	* May generate verbose code depending on the input.
	* Long code generation may exceed token limits.
	* Ambiguous instructions can lead to incomplete or incorrect code.
	* Prioritizes efficiency in code generation.

	### <span style="color: #FF6347;">Safety</span>
	* Avoids generating harmful or malicious code.
	* Will not assist with illegal or unethical activities.

	## 📚 <span style="background: linear-gradient(45deg, #FF6347, #FFD700); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Citation</span>

	```bibtex
	@misc{cipher2024,
	author = {Abhay Koul},
	title = {Cipher-20B: Your Ultimate Code Buddy},
	year = {2024},
	publisher = {HelpingAI},
	journal = {HuggingFace},
	howpublished = {\url{https://huggingface.co/HelpingAI/Cipher-20B}}
	}
	```

	Built with dedication, precision, and passion by HelpingAI

	[Website](https://helpingai.co) • [GitHub](https://github.com/HelpingAI) • [Discord](https://discord.gg/YweJwNqrnH) • [HuggingFace](https://huggingface.co/HelpingAI)