Instructions to use kai-os/Grug-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kai-os/Grug-12B with Transformers:

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

pipe = pipeline("text-generation", model="kai-os/Grug-12B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("kai-os/Grug-12B")
model = AutoModelForMultimodalLM.from_pretrained("kai-os/Grug-12B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kai-os/Grug-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kai-os/Grug-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kai-os/Grug-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kai-os/Grug-12B

SGLang

How to use kai-os/Grug-12B 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 "kai-os/Grug-12B" \
    --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": "kai-os/Grug-12B",
		"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 "kai-os/Grug-12B" \
        --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": "kai-os/Grug-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kai-os/Grug-12B with Docker Model Runner:
```
docker model run hf.co/kai-os/Grug-12B
```

kai-os commited on Jul 2

Commit

aa0b2c1

verified ·

1 Parent(s): 84cd2ee

Clean public metadata and model card wording

Browse files

Files changed (1) hide show

README.md +17 -8

README.md CHANGED Viewed

@@ -11,7 +11,6 @@ tags:
 - qlora
 - reasoning
 - compact-reasoning
-- grugthink
 - gemma-4
 datasets:
 - hotdogs/uka-glm-5.2
@@ -48,17 +47,11 @@ model-index:
 Grug 12B is a compact-reasoning fine-tune of `google/gemma-4-12B-it`.
 It was trained to keep the useful information from a reasoning trace while
-making the trace shorter, more direct, and less polished.
 This repository is published as merged Transformers/safetensors model weights.
 It was trained with QLoRA, then merged into the base model for release.
-## GGUF
-A llama.cpp `Q4_K_M` GGUF release is available in the adjacent repo:
-[`kai-os/Grug-12B-GGUF`](https://huggingface.co/kai-os/Grug-12B-GGUF).
 ## What Changed
 The training target is a terse internal-reasoning style: short high-density
@@ -69,6 +62,22 @@ The goal is lower reasoning-token usage relative to the base model while
 preserving answer quality. It is not meant to hide uncertainty or remove needed
 reasoning.
 Final verified source mix:
 | Source | License | Domain | Verified rows |

 - qlora
 - reasoning
 - compact-reasoning
 - gemma-4
 datasets:
 - hotdogs/uka-glm-5.2
 Grug 12B is a compact-reasoning fine-tune of `google/gemma-4-12B-it`.
 It was trained to keep the useful information from a reasoning trace while
+making the trace shorter, denser, and less verbose.
 This repository is published as merged Transformers/safetensors model weights.
 It was trained with QLoRA, then merged into the base model for release.
 ## What Changed
 The training target is a terse internal-reasoning style: short high-density
 preserving answer quality. It is not meant to hide uncertainty or remove needed
 reasoning.
+## Training Data
+The data pipeline started from a recent, filtered reasoning pool and converted
+verbose traces into compact traces before SFT packing.
+Source gate:
+- Run date: June 30, 2026.
+- Default freshness cutoff: 45 days. Sources older than May 16, 2026 were
+  rejected unless manually allowed.
+- Allowed train licenses: MIT, Apache-2.0, CC-BY-4.0, CC0-1.0.
+- Hard reject terms included OpenAI, ChatGPT, GPT-5, Claude, Anthropic, Opus,
+  Sonnet, and Gemini.
+- Soft-risk sources marked as synthetic/distill were manually reviewed or
+  rejected depending on provenance and license.
 Final verified source mix:
 | Source | License | Domain | Verified rows |