Instructions to use FourOhFour/Zenith_4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FourOhFour/Zenith_4B with Transformers:

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

pipe = pipeline("text-generation", model="FourOhFour/Zenith_4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FourOhFour/Zenith_4B")
model = AutoModelForCausalLM.from_pretrained("FourOhFour/Zenith_4B")
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 FourOhFour/Zenith_4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FourOhFour/Zenith_4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FourOhFour/Zenith_4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FourOhFour/Zenith_4B

SGLang

How to use FourOhFour/Zenith_4B 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 "FourOhFour/Zenith_4B" \
    --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": "FourOhFour/Zenith_4B",
		"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 "FourOhFour/Zenith_4B" \
        --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": "FourOhFour/Zenith_4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FourOhFour/Zenith_4B with Docker Model Runner:
```
docker model run hf.co/FourOhFour/Zenith_4B
```

jeiku commited on Sep 2, 2024

Commit

56e5fa3

verified ·

1 Parent(s): 29cc18c

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -6,6 +6,17 @@ library_name: transformers
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/ZfpTTVXP15L0F9PEJ56Re.png)
 This model was created with the help of several members of Anthracite.
 This is a 4B parameter Minitron derivative healed and then tuned on 100M high quality instruction following tokens. This model was tuned at 8k context. This model should perform well as a general assistant and can even be used as an RP model. Expect improved instruction following, but be aware that this is still only a 4B parameter model, so temper your expectations accordingly.

 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/ZfpTTVXP15L0F9PEJ56Re.png)
+```
+|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
+|------------------|------:|------|------|------|---|-----:|---|-----:|
+|mmlu              |      2|none  |      |acc   |_  |0.5922|_  |0.0039|
+| - humanities     |      2|none  |      |acc   |_  |0.5522|_  |0.0068|
+| - other          |      2|none  |      |acc   |_  |0.6579|_  |0.0082|
+| - social sciences|      2|none  |      |acc   |_  |0.6815|_  |0.0082|
+| - stem           |      2|none  |      |acc   |_  |0.5002|_  |0.0086|
+```
 This model was created with the help of several members of Anthracite.
 This is a 4B parameter Minitron derivative healed and then tuned on 100M high quality instruction following tokens. This model was tuned at 8k context. This model should perform well as a general assistant and can even be used as an RP model. Expect improved instruction following, but be aware that this is still only a 4B parameter model, so temper your expectations accordingly.