Instructions to use MatteoKhan/Cerebras-OPT-Fusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MatteoKhan/Cerebras-OPT-Fusion with Transformers:

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

pipe = pipeline("text-generation", model="MatteoKhan/Cerebras-OPT-Fusion")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MatteoKhan/Cerebras-OPT-Fusion")
model = AutoModelForCausalLM.from_pretrained("MatteoKhan/Cerebras-OPT-Fusion")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MatteoKhan/Cerebras-OPT-Fusion with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MatteoKhan/Cerebras-OPT-Fusion"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MatteoKhan/Cerebras-OPT-Fusion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MatteoKhan/Cerebras-OPT-Fusion

SGLang

How to use MatteoKhan/Cerebras-OPT-Fusion 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 "MatteoKhan/Cerebras-OPT-Fusion" \
    --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": "MatteoKhan/Cerebras-OPT-Fusion",
		"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 "MatteoKhan/Cerebras-OPT-Fusion" \
        --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": "MatteoKhan/Cerebras-OPT-Fusion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MatteoKhan/Cerebras-OPT-Fusion with Docker Model Runner:
```
docker model run hf.co/MatteoKhan/Cerebras-OPT-Fusion
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🚀 CerebrasOPT-Hybrid-6.7B: A Balanced Fusion of Strength & Efficiency

📌 Overview

CerebrasOPT-Hybrid-6.7B is an experimental hybrid language model that merges the capabilities of Cerebras-GPT-6.7B and OPT-6.7B using the Linear Merge technique. This approach aims to enhance performance while maintaining efficiency, leveraging the best of both parent models.

🔗 Created by: [Matteo Khan]
🎓 Affiliation: Apprentice at TW3 Partners (Generative AI Research) 📍 License: MIT

🔗 Connect with me on LinkedIn
🔗 Model on Hugging Face

🧠 Model Details

Model Type: Hybrid Language Model (Merged)
Parent Models:
- Cerebras-GPT-6.7B
- OPT-6.7B
Merging Technique: Linear Merge (MergeKit)

🎯 Intended Use

This model is primarily intended for research and experimentation in hybrid model optimization. Possible applications include:

✅ Text Generation
✅ Conversational AI
✅ Creative Writing Assistance
✅ Exploration of Model Merging Effects

⚠️ Limitations & Considerations

While CerebrasOPT-Hybrid-6.7B provides enhanced capabilities, it also inherits certain limitations from its parent models:

❌ May generate inaccurate or misleading information
⚠️ Potential for biased, offensive, or harmful content
🔄 Merging may introduce unpredictable behaviors
📉 Performance may vary across different tasks

🔬 Merging Process & Configuration

This is not a newly trained model, but rather a merge of existing models using the following configuration:

merge_method: linear
dtype: float16
models:
  - model: "cerebras/Cerebras-GPT-6.7B"
    parameters:
      t: 1.0
      weight: 0.5
  - model: "facebook/opt-6.7b"
    parameters:
      t: 1.0
      weight: 0.5

parameters:
  normalize: true
  int8_mask: false

layers:
  - pattern: "model.*"

📊 No formal evaluation has been conducted yet. Users are encouraged to benchmark and share feedback!

🌍 Environmental Impact

By utilizing model merging instead of training from scratch, CerebrasOPT-Hybrid-6.7B significantly reduces computational and environmental costs.

🚀 How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "YourProfile/CerebrasOPT-Hybrid-6.7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example usage
prompt = "Describe the future of AI in a short paragraph."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

📝 Citation

@misc{cerebrasopt2025,
      title={CerebrasOPT: A Hybrid Open-Source Language Model},
      author={Your Name},
      year={2025},
      eprint={arXiv:XXXX.XXXXX},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📩 Feedback & Contact: Reach out via Hugging Face.

🎉 Happy Experimenting! 🚀

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F16

Model tree for MatteoKhan/Cerebras-OPT-Fusion

Base model

cerebras/Cerebras-GPT-6.7B

Finetuned

(2)

this model

Quantizations

2 models