Instructions to use TitleOS/RocketZephyr-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TitleOS/RocketZephyr-3b with Transformers:

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

pipe = pipeline("text-generation", model="TitleOS/RocketZephyr-3b", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TitleOS/RocketZephyr-3b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TitleOS/RocketZephyr-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TitleOS/RocketZephyr-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TitleOS/RocketZephyr-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TitleOS/RocketZephyr-3b

SGLang

How to use TitleOS/RocketZephyr-3b 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 "TitleOS/RocketZephyr-3b" \
    --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": "TitleOS/RocketZephyr-3b",
		"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 "TitleOS/RocketZephyr-3b" \
        --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": "TitleOS/RocketZephyr-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TitleOS/RocketZephyr-3b with Docker Model Runner:
```
docker model run hf.co/TitleOS/RocketZephyr-3b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

RocketZephyr-3B

An attempt at creating a 3B parameter merged model using StabilityAI's Zephyr-3b and Pansophic's Rocket-3B.

Repo Description

This repo serves as an housing for my experimentation with creating a 3 billion parameter merged model using mergekit

Merged Models: stabilityai/stablelm-zephyr-3b & pansophic/rocket-3B
Merge Weights: 1.0 & 0.3
Merge Method: Linear
License: I believe this (current) model inherits the Stable Non-Commercial Research Community License Agreement and as such is licensed by it as well.

Downloads last month: 18

Safetensors

Model size

3B params

Tensor type

F16

Model tree for TitleOS/RocketZephyr-3b

Quantizations

1 model