Instructions to use zen-E/deepspeed-chat-step1-model-opt1.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zen-E/deepspeed-chat-step1-model-opt1.3b with Transformers:

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

pipe = pipeline("text-generation", model="zen-E/deepspeed-chat-step1-model-opt1.3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zen-E/deepspeed-chat-step1-model-opt1.3b")
model = AutoModelForCausalLM.from_pretrained("zen-E/deepspeed-chat-step1-model-opt1.3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zen-E/deepspeed-chat-step1-model-opt1.3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zen-E/deepspeed-chat-step1-model-opt1.3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zen-E/deepspeed-chat-step1-model-opt1.3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zen-E/deepspeed-chat-step1-model-opt1.3b

SGLang

How to use zen-E/deepspeed-chat-step1-model-opt1.3b 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 "zen-E/deepspeed-chat-step1-model-opt1.3b" \
    --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": "zen-E/deepspeed-chat-step1-model-opt1.3b",
		"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 "zen-E/deepspeed-chat-step1-model-opt1.3b" \
        --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": "zen-E/deepspeed-chat-step1-model-opt1.3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zen-E/deepspeed-chat-step1-model-opt1.3b with Docker Model Runner:
```
docker model run hf.co/zen-E/deepspeed-chat-step1-model-opt1.3b
```

deepspeed-chat-step1-model-opt1.3b / pytorch_model.bin

zen-E

Add model weights and configurations

449d71f over 3 years ago

Download

History Blame Contribute Delete

2.63 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 0a5816355990ea0d546b77918f0c19c0b4bdaaa3bc340503fa024a7d6e4e2374
Size of remote file:: 2.63 GB
SHA256:: 2c54d7b4126bf457392807eb619e5983a9de9cc068bd4c6b6e2a1c2b797781c8

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.