Instructions to use TinyPixel/qwen-1.8B-OrcaMini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TinyPixel/qwen-1.8B-OrcaMini with Transformers:

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

pipe = pipeline("text-generation", model="TinyPixel/qwen-1.8B-OrcaMini", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TinyPixel/qwen-1.8B-OrcaMini", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TinyPixel/qwen-1.8B-OrcaMini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TinyPixel/qwen-1.8B-OrcaMini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TinyPixel/qwen-1.8B-OrcaMini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TinyPixel/qwen-1.8B-OrcaMini

SGLang

How to use TinyPixel/qwen-1.8B-OrcaMini 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 "TinyPixel/qwen-1.8B-OrcaMini" \
    --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": "TinyPixel/qwen-1.8B-OrcaMini",
		"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 "TinyPixel/qwen-1.8B-OrcaMini" \
        --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": "TinyPixel/qwen-1.8B-OrcaMini",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TinyPixel/qwen-1.8B-OrcaMini with Docker Model Runner:
```
docker model run hf.co/TinyPixel/qwen-1.8B-OrcaMini
```

TinyPixel commited on Jan 6, 2024

Commit

cf93b5c

1 Parent(s): c314399

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -0

README.md CHANGED Viewed

@@ -3,3 +3,31 @@ datasets:
 - TinyPixel/orca-bad
 ---

 - TinyPixel/orca-bad
 ---
+## Usage
+```python
+!pip install -q -U trl transformers accelerate git+https://github.com/huggingface/peft.git
+!pip install -q datasets bitsandbytes einops wandb sentencepiece transformers_stream_generator tiktoken
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+tokenizer = AutoTokenizer.from_pretrained("TinyPixel/qwen-1.8B-OrcaMini", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("TinyPixel/qwen-1.8B-OrcaMini", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
+device = "cuda:0"
+text = '''SYSTEM:
+USER: what is the difference between a dog and a cat on a biological level?
+ASSISTANT:'''
+inputs = tokenizer(text, return_tensors="pt").to(device)
+outputs = model.generate(**inputs,
+              max_new_tokens=512,
+              do_sample=True,
+              top_p=0.95,
+              temperature=0.7,
+              top_k=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```