Instructions to use auryn-macmillan/fuse-1-Lite-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use auryn-macmillan/fuse-1-Lite-v2 with Transformers:

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

pipe = pipeline("text-generation", model="auryn-macmillan/fuse-1-Lite-v2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("auryn-macmillan/fuse-1-Lite-v2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use auryn-macmillan/fuse-1-Lite-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "auryn-macmillan/fuse-1-Lite-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "auryn-macmillan/fuse-1-Lite-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/auryn-macmillan/fuse-1-Lite-v2

SGLang

How to use auryn-macmillan/fuse-1-Lite-v2 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 "auryn-macmillan/fuse-1-Lite-v2" \
    --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": "auryn-macmillan/fuse-1-Lite-v2",
		"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 "auryn-macmillan/fuse-1-Lite-v2" \
        --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": "auryn-macmillan/fuse-1-Lite-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use auryn-macmillan/fuse-1-Lite-v2 with Docker Model Runner:
```
docker model run hf.co/auryn-macmillan/fuse-1-Lite-v2
```

Fuse-1 Lite v2

Fuse-1 Lite v2 is the trained successor of Akahisrr/fuse-1-Lite. It adds a v2 coding-expert pathway on top of the v1 model: bridge layers that map LFM2 representations to Qwen3.6-style coding experts, a router, an expert scale, and a coding gate — trained with KL distillation to the LFM2 teacher.

Base architecture: Fuse3V2ForCausalLM (model_type = fuse3_v2)
Trained: 550 steps (3 stages: foundation, representation mapping, router/refinement)
Trainable params: ~253.7M (bridge, router, coding norm/gate, expert scale)
Distillation: KL to LiquidAI/LFM2.5-2.6B (alpha=0.5)

⚠️ Custom code — trust_remote_code=True

This model uses a custom architecture and requires:

from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
    "auryn-macmillan/fuse-1-Lite-v2", trust_remote_code=True,
    torch_dtype="bfloat16",
)

trust_remote_code=True executes the custom Python code shipped in this repo (fuse3_model_v2.py). This is the same trust model as the upstream Akahisrr/fuse-1-Lite model. Please review the custom code before use and only run it in an environment where executing untrusted code is acceptable.

Quickstart

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "auryn-macmillan/fuse-1-Lite-v2"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, trust_remote_code=True
).cuda()
model.eval()
prompt = "Write a Python function to check if a number is prime."
inputs = tok(prompt, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=128)
print(tok.decode(out[0]))

Files

model.safetensors — merged full model weights (v1 base + trained v2 params)
config.json — model_type=fuse3_v2, auto_map to fuse3_model_v2.py
fuse3_model_v2.py, fuse3_model.py — custom model code (requires trust_remote_code)
tokenizer files (tokenizer.json, tokenizer_config.json, chat_template.jinja)

Notes

The coding experts are gated; set model.set_coding_enabled(False) to run the pure LFM2 pathway.
Training was performed in an isolated container; this repository contains no training code or data.

Downloads last month: -

Safetensors

Model size

6B params

Tensor type

BF16