Image-Text-to-Text
Transformers
Safetensors
multilingual
qwen3_5_text
text-generation
llm
neuralnode
horus
tokenai
conversational
Instructions to use tokenaii/Horus-Hiero-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tokenaii/Horus-Hiero-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tokenaii/Horus-Hiero-9B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tokenaii/Horus-Hiero-9B") model = AutoModelForCausalLM.from_pretrained("tokenaii/Horus-Hiero-9B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] 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 Settings
- vLLM
How to use tokenaii/Horus-Hiero-9B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tokenaii/Horus-Hiero-9B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tokenaii/Horus-Hiero-9B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/tokenaii/Horus-Hiero-9B
- SGLang
How to use tokenaii/Horus-Hiero-9B 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 "tokenaii/Horus-Hiero-9B" \ --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": "tokenaii/Horus-Hiero-9B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "tokenaii/Horus-Hiero-9B" \ --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": "tokenaii/Horus-Hiero-9B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use tokenaii/Horus-Hiero-9B with Docker Model Runner:
docker model run hf.co/tokenaii/Horus-Hiero-9B
Upload neuralnode_example.py with huggingface_hub
Browse files- neuralnode_example.py +40 -0
neuralnode_example.py
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Horus Hiero โ NeuralNode Example Script"""
|
| 2 |
+
import neuralnode as nn
|
| 3 |
+
|
| 4 |
+
# --- Configuration ---
|
| 5 |
+
MODEL_ID = "tokenaii/Horus-Hiero-9B-GGUF/Horus-Hiero-9B-Q6_K.gguf"
|
| 6 |
+
# For Mini version: "tokenaii/Horus-Hiero-Mini-4B-GGUF/Horus-Hiero-Mini-4B-Q6_K.gguf"
|
| 7 |
+
DEVICE = "cpu" # Change to "cuda" for GPU acceleration
|
| 8 |
+
|
| 9 |
+
# --- Load model ---
|
| 10 |
+
model = nn.HorusModel(MODEL_ID, device=DEVICE).load()
|
| 11 |
+
|
| 12 |
+
# --- Basic Chat ---
|
| 13 |
+
response = model.chat([
|
| 14 |
+
{"role": "user", "content": "What is Horus Hiero?"}
|
| 15 |
+
])
|
| 16 |
+
print("Basic Chat:", response.content)
|
| 17 |
+
|
| 18 |
+
# --- Streaming ---
|
| 19 |
+
print("\n--- Streaming ---")
|
| 20 |
+
chunks = model.chat([
|
| 21 |
+
{"role": "user", "content": "Write a short introduction about ancient Egyptian writing."}
|
| 22 |
+
], stream=True)
|
| 23 |
+
for chunk in chunks:
|
| 24 |
+
if chunk.content:
|
| 25 |
+
print(chunk.content, end="", flush=True)
|
| 26 |
+
print()
|
| 27 |
+
|
| 28 |
+
# --- Thinking Mode ---
|
| 29 |
+
print("\n--- Thinking Mode ---")
|
| 30 |
+
response = model.chat([
|
| 31 |
+
{"role": "user", "content": "What is 7 plus 5? Reply in one sentence."}
|
| 32 |
+
], thinking=True, show_thinking=False)
|
| 33 |
+
print("Answer:", response.content)
|
| 34 |
+
|
| 35 |
+
# --- Hieroglyphic Translation ---
|
| 36 |
+
print("\n--- Hieroglyphic Translation ---")
|
| 37 |
+
response = model.chat([
|
| 38 |
+
{"role": "user", "content": 'Translate this hieroglyph to English: ๐๐๐๐'}
|
| 39 |
+
])
|
| 40 |
+
print("Translation:", response.content)
|