Instructions to use spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16")
model = AutoModelForCausalLM.from_pretrained("spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16")
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 spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16

SGLang

How to use spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16 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 "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16" \
    --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": "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16",
		"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 "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16" \
        --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": "spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16 with Docker Model Runner:
```
docker model run hf.co/spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

hy3-spellbound-simpo-step151-merged-bf16

Merged bf16 checkpoint built from:

tencent/hy3-preview
spellbound-eng/hy3-preview-spellbound-lora-v0.1-20260531-step5355
spellbound-eng/hy3-spellbound-simpo-r256-b10-g3-sft0p1-lr2e-6-step151-lora

The adapters were merged sequentially and saved as safetensors shards with a 6GB shard limit.

This repository is manually gated.

Downloads last month: 6

Safetensors

Model size

295B params

Tensor type

F32

BF16

Model tree for spellbound-eng/hy3-spellbound-simpo-step151-merged-bf16

Quantizations

1 model