Instructions to use MatteoKhan/TinyStable-Hybrid-1.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MatteoKhan/TinyStable-Hybrid-1.6B with Transformers:

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

pipe = pipeline("text-generation", model="MatteoKhan/TinyStable-Hybrid-1.6B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MatteoKhan/TinyStable-Hybrid-1.6B")
model = AutoModelForCausalLM.from_pretrained("MatteoKhan/TinyStable-Hybrid-1.6B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MatteoKhan/TinyStable-Hybrid-1.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MatteoKhan/TinyStable-Hybrid-1.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MatteoKhan/TinyStable-Hybrid-1.6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MatteoKhan/TinyStable-Hybrid-1.6B

SGLang

How to use MatteoKhan/TinyStable-Hybrid-1.6B 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/TinyStable-Hybrid-1.6B" \
    --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/TinyStable-Hybrid-1.6B",
		"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/TinyStable-Hybrid-1.6B" \
        --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/TinyStable-Hybrid-1.6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MatteoKhan/TinyStable-Hybrid-1.6B with Docker Model Runner:
```
docker model run hf.co/MatteoKhan/TinyStable-Hybrid-1.6B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🚀 TinyStable-Hybrid-1.6B: Merging Efficiency & Power

📌 Overview

TinyStable-Hybrid-1.6B is an experimental hybrid language model that merges the capabilities of TinyLlama and StableLM. Built using MergeKit, this model is designed to balance performance and efficiency while offering strong text generation capabilities.

🔗 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:
- TinyLlama-1.1B-Chat-v1.0
- TinyLlama-1.1B-intermediate-step-1431k-3T
Merging Technique: Linear Merge (MergeKit)

🎯 Intended Use

This model is primarily intended for research and experimentation in hybrid model optimization. Potential use cases include:

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

⚠️ Limitations & Considerations

While TinyStable-Hybrid-1.6B offers 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: "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
    parameters:
      t: 1.0
      weight: 0.5
  - model: "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
    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 rather than training from scratch, TinyStable-Hybrid-1.6B significantly reduces computational and environmental costs.

🚀 How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "MatteoKhan/TinyStable-Hybrid-1.6B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example usage
prompt = "Write a short poem about artificial intelligence."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

📝 TinyLlama

@misc{zhang2024tinyllama,
      title={TinyLlama: An Open-Source Small Language Model},
      author={Jiayu Zhang and others},
      year={2024},
      eprint={2401.02385},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📩 Feedback & Contact: Reach out via Hugging Face.

🎉 Happy Experimenting! 🚀

Downloads last month: 18

Safetensors

Model size

1B params

Tensor type

F32

Model tree for MatteoKhan/TinyStable-Hybrid-1.6B

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Finetuned

(576)

this model

Quantizations

1 model

Paper for MatteoKhan/TinyStable-Hybrid-1.6B

TinyLlama: An Open-Source Small Language Model

Paper • 2401.02385 • Published Jan 4, 2024 • 96