Instructions to use tensoropera/Fox-1-1.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensoropera/Fox-1-1.6B with Transformers:

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

pipe = pipeline("text-generation", model="tensoropera/Fox-1-1.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tensoropera/Fox-1-1.6B")
model = AutoModelForCausalLM.from_pretrained("tensoropera/Fox-1-1.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tensoropera/Fox-1-1.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensoropera/Fox-1-1.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensoropera/Fox-1-1.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensoropera/Fox-1-1.6B

SGLang

How to use tensoropera/Fox-1-1.6B 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 "tensoropera/Fox-1-1.6B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensoropera/Fox-1-1.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tensoropera/Fox-1-1.6B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensoropera/Fox-1-1.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tensoropera/Fox-1-1.6B with Docker Model Runner:
```
docker model run hf.co/tensoropera/Fox-1-1.6B
```

zijianhu commited on Nov 21, 2024

Commit

d13ba2d

verified ·

1 Parent(s): 3c2bd69

Update README.md

Browse files

Add technical report link

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -113,8 +113,8 @@ by [TensorOpera AI](https://tensoropera.ai/). The model was trained with a 3-sta
 tokens of text and code data in 8K sequence length. Fox-1 uses Grouped Query Attention (GQA) with 4 key-value heads and
 16 attention heads for faster inference.
-For the full details of this model please read
-our [release blog post](https://blog.tensoropera.ai/tensoropera-unveils-fox-foundation-model-a-pioneering-open-source-slm-leading-the-way-against-tech-giants).
 ## Benchmarks

 tokens of text and code data in 8K sequence length. Fox-1 uses Grouped Query Attention (GQA) with 4 key-value heads and
 16 attention heads for faster inference.
+For the full details of this model please read [Fox-1 technical report](https://arxiv.org/abs/2411.05281)
+and [release blog post](https://blog.tensoropera.ai/tensoropera-unveils-fox-foundation-model-a-pioneering-open-source-slm-leading-the-way-against-tech-giants).
 ## Benchmarks