Instructions to use trohrbaugh/Hy3-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trohrbaugh/Hy3-heretic with Transformers:

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

pipe = pipeline("text-generation", model="trohrbaugh/Hy3-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trohrbaugh/Hy3-heretic")
model = AutoModelForCausalLM.from_pretrained("trohrbaugh/Hy3-heretic", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trohrbaugh/Hy3-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trohrbaugh/Hy3-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trohrbaugh/Hy3-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trohrbaugh/Hy3-heretic

SGLang

How to use trohrbaugh/Hy3-heretic 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 "trohrbaugh/Hy3-heretic" \
    --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": "trohrbaugh/Hy3-heretic",
		"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 "trohrbaugh/Hy3-heretic" \
        --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": "trohrbaugh/Hy3-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trohrbaugh/Hy3-heretic with Docker Model Runner:
```
docker model run hf.co/trohrbaugh/Hy3-heretic
```

Can you create awq int 4 version?

by denisvasi - opened Jul 11

Discussion

denisvasi

Jul 11

•

edited Jul 11

Can you create awq int 4 version, please?

trohrbaugh

Owner Jul 13

I by and large only publish the BF16 to be a transparent as possible from a risk to use point of view. "Decensoring" takes alot of compute/gpu time but compressing is also costly and there are so many options. For example if someone is using Blackwell you would want a NVFP4 today. Maybe some folks here and like unsloth does for ggufs can pick up the baton and share the effort?

trohrbaugh changed discussion status to closed Jul 13

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