Instructions to use laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 with Transformers:

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

pipe = pipeline("text-generation", model="laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888

SGLang

How to use laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 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 "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888" \
    --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": "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888",
		"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 "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888" \
        --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": "laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 with Docker Model Runner:
```
docker model run hf.co/laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888
```

Snowball 67B-A2B Nemotron-Terminal SFT

This repository contains BF16 Hugging Face/vLLM exports from the Nemotron-Terminal branch of Marin's ordered Chat → Thinking → Agentic SFT campaign. The model was initialized from the final Thinking checkpoint and trained for 1,888 steps on the Nemotron Terminal corpus used by the successful control in marin-community/marin#7743.

main is the final step-1,888 checkpoint. Retained intermediate checkpoints are published as step-N branches.

Provenance

Native checkpoint collection:

s3://marin-us-east-02a/marin/grug/snowball_step105149_sft_s3_nemotron_terminal_steps1888/2026.08.14.1/checkpoints/

The export preserves the Marin tokenizer, Delphi special tokens, and the trained FP32 query-bias state. This lineage should be evaluated with Terminus-2.

Downloads last month: 6,717

Safetensors

Model size

67B params

Tensor type

BF16

Model tree for laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888

Finetunes

7 models