Instructions to use hitonet/hito-1.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hitonet/hito-1.7b with Transformers:

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

pipe = pipeline("text-generation", model="hitonet/hito-1.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hitonet/hito-1.7b")
model = AutoModelForCausalLM.from_pretrained("hitonet/hito-1.7b", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hitonet/hito-1.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hitonet/hito-1.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hitonet/hito-1.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hitonet/hito-1.7b

SGLang

How to use hitonet/hito-1.7b 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 "hitonet/hito-1.7b" \
    --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": "hitonet/hito-1.7b",
		"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 "hitonet/hito-1.7b" \
        --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": "hitonet/hito-1.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hitonet/hito-1.7b with Docker Model Runner:
```
docker model run hf.co/hitonet/hito-1.7b
```

The Test Results are Fake! It Spreads Misinformation!

by qpqpqpqpqpqp - opened Dec 13, 2025

Discussion

qpqpqpqpqpqp

Dec 13, 2025

The 'The Bat and Ball Test' is very interesting, but your results are fake and made up, tried yourself? I was curious and did it myself, just look at it

qpqpqpqpqpqp

Dec 13, 2025

Deepseek 7B https://files.catbox.moe/103jud.jpg

hitonet

Owner Dec 13, 2025

Hi,

Thanks for the review but please dont judge by using low quantization. Run the main model wieghts thats what we used for test.

Some community members uploaded better quantized file.

Also from the screenahot i cant see our custom tags loaded. Are you not rendering them on the front end or your screenshot is from another model? Please get the official gguf q8 works perfectly fine. You should see etc.

If you need help let me know and remember production model is on https://chat.hitonet.com

Hope i helped you.

hitonet

Owner Dec 13, 2025

Also our test was ran automatically no editing involved we use a python file that runs exact prompt on all test subjects and generate the results.

Its accurate try to use different tempreture or 0

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment