Instructions to use Fu01978/Nano-H with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Fu01978/Nano-H with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Fu01978/Nano-H")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Fu01978/Nano-H", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Fu01978/Nano-H with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Fu01978/Nano-H" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Fu01978/Nano-H", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Fu01978/Nano-H
- SGLang
How to use Fu01978/Nano-H 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 "Fu01978/Nano-H" \ --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": "Fu01978/Nano-H", "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 "Fu01978/Nano-H" \ --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": "Fu01978/Nano-H", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Fu01978/Nano-H with Docker Model Runner:
docker model run hf.co/Fu01978/Nano-H
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
metrics:
|
| 4 |
+
- accuracy
|
| 5 |
+
widget:
|
| 6 |
+
- text: "What is the meaning of life?"
|
| 7 |
+
example_title: "Philosophy"
|
| 8 |
+
- text: "How do I build a rocket?"
|
| 9 |
+
example_title: "Engineering"
|
| 10 |
+
library_name: transformers
|
| 11 |
+
tags:
|
| 12 |
+
- h_model
|
| 13 |
+
- ultra-efficient
|
| 14 |
+
- nano-ai
|
| 15 |
+
- 2-params
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# Nano-H: The World's First `h_model`
|
| 19 |
+
|
| 20 |
+
## Key Features
|
| 21 |
+
* **Architecture:** `h_model`
|
| 22 |
+
* **Parameter Count:** 2
|
| 23 |
+
* **Vocabulary Size:** 1 ("H")
|
| 24 |
+
* **Inference Latency:** Measured in nanoseconds
|
| 25 |
+
|
| 26 |
+
## Benchmarks
|
| 27 |
+
| Benchmark | Nano-H Score |
|
| 28 |
+
| :--- | :--- | :--- |
|
| 29 |
+
| **Output Consistency** | **100%** |
|
| 30 |
+
| **H-Accuracy** | **100%** |
|
| 31 |
+
|
| 32 |
+
## Usage
|
| 33 |
+
To experience the definitive power of the `h_model` architecture, load it with `trust_remote_code=True`:
|
| 34 |
+
|
| 35 |
+
```python
|
| 36 |
+
from transformers import AutoModel, AutoTokenizer
|
| 37 |
+
|
| 38 |
+
model_path = "Fu01978/Nano-H"
|
| 39 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 40 |
+
model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
|
| 41 |
+
|
| 42 |
+
inputs = tokenizer("Hello?", return_tensors="pt")
|
| 43 |
+
outputs = model.generate(inputs["input_ids"], max_length=1)
|
| 44 |
+
print(tokenizer.decode(outputs[0]))
|
| 45 |
+
```
|
| 46 |
+
## Safety & Alignment
|
| 47 |
+
Nano-H is inherently safe. It cannot be jailbroken to provide instructions for dangerous activities, as any such request will be met with a singular "H".
|
| 48 |
+
|