Instructions to use colesmcintosh/Halcyon-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use colesmcintosh/Halcyon-1B with Transformers:

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

pipe = pipeline("text-generation", model="colesmcintosh/Halcyon-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("colesmcintosh/Halcyon-1B")
model = AutoModelForCausalLM.from_pretrained("colesmcintosh/Halcyon-1B", 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 colesmcintosh/Halcyon-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "colesmcintosh/Halcyon-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "colesmcintosh/Halcyon-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/colesmcintosh/Halcyon-1B

SGLang

How to use colesmcintosh/Halcyon-1B 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 "colesmcintosh/Halcyon-1B" \
    --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": "colesmcintosh/Halcyon-1B",
		"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 "colesmcintosh/Halcyon-1B" \
        --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": "colesmcintosh/Halcyon-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use colesmcintosh/Halcyon-1B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for colesmcintosh/Halcyon-1B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for colesmcintosh/Halcyon-1B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for colesmcintosh/Halcyon-1B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="colesmcintosh/Halcyon-1B",
    max_seq_length=2048,
)

Docker Model Runner
How to use colesmcintosh/Halcyon-1B with Docker Model Runner:
```
docker model run hf.co/colesmcintosh/Halcyon-1B
```

Halcyon-1B / README.md

colesmcintosh

Update README.md

64d2e8c verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

2.64 kB

metadata

base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - gemma3_text
license: apache-2.0
language:
  - en
datasets:
  - Nitral-AI/Creative_Writing-ShareGPT

Halcyon-1B

Halcyon-1B is a creatively fine-tuned variant of the unsloth/gemma-3-1b-it-unsloth-bnb-4bit model, specifically tailored for imaginative and expressive creative writing tasks. This model has been fine-tuned to excel in storytelling, literary exploration, and nuanced narrative construction.

Model Details

Developed by: colesmcintosh
Base Model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
Fine-tuning Methodology: Trained 2x faster leveraging Unsloth and Huggingface's TRL library.

Dataset

This model was fine-tuned using the (Nitral-AI) Creative Writing ShareGPT dataset.

Capabilities

Creative Writing: Exceptional at generating narratives, stories, poetry, and prose.
Expressive Nuance: Generates sophisticated, context-aware, and evocative literary outputs.
Versatility: Suitable for writers, creators, educators, and storytellers looking to harness AI for enhanced creative exploration.

Intended Use

Creative Inspiration: Idea generation, overcoming writer’s block, and expanding narrative horizons.
Educational Tools: Supporting literature courses, workshops, and creative writing sessions.
Interactive Storytelling: Enabling interactive fiction, dynamic content creation, and innovative narrative formats.

Usage

You can quickly test Halcyon-1B using Huggingface Transformers:

from unsloth import FastModel
from transformers import TextStreamer

# Load model and tokenizer
model, tokenizer = FastModel.from_pretrained(
    model_name = "colesmcintosh/Halcyon-1B",
    max_seq_length = 2048,
    load_in_4bit = True,
)

# Format prompt using Gemma-3 chat template
messages = [{
    "role": "user",
    "content": [{"type" : "text", "text" : "Write a mythological tale about how the oceans came to be."}]
}]

text_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
text_str = tokenizer.decode(text_ids)

# Generate response
outputs = model.generate(
    **tokenizer([text_str], return_tensors="pt").to("cuda"),
    max_new_tokens=64,
    temperature=1.0,
    top_p=0.95,
    top_k=64,
    streamer=TextStreamer(tokenizer, skip_prompt=True),
)