Instructions to use klusai/tf2-12b-w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use klusai/tf2-12b-w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="klusai/tf2-12b-w8a8")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("klusai/tf2-12b-w8a8")
model = AutoModelForImageTextToText.from_pretrained("klusai/tf2-12b-w8a8")
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

vLLM

How to use klusai/tf2-12b-w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "klusai/tf2-12b-w8a8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "klusai/tf2-12b-w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/klusai/tf2-12b-w8a8

SGLang

How to use klusai/tf2-12b-w8a8 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 "klusai/tf2-12b-w8a8" \
    --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": "klusai/tf2-12b-w8a8",
		"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 "klusai/tf2-12b-w8a8" \
        --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": "klusai/tf2-12b-w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use klusai/tf2-12b-w8a8 with Docker Model Runner:
```
docker model run hf.co/klusai/tf2-12b-w8a8
```

🦊 klusai/tf2-12b-w8a8 — EN→RO Translator (W8A8 via LLM Compressor)

Gemma 3 12B (Instruct), LoRA-tuned on 15k English→Romanian fable pairs (synthetic, GPT-o3), then compressed to W8A8 (INT8 weights & activations) using LLM Compressor by vLLM for fast, memory-efficient inference.

Focus: faithful, fluent EN→RO translations of short moral fables, preserving tone/structure and proper Romanian diacritics.

✨ What’s in this build

Training: Same LoRA fine-tune as [tf2-12b-gguf](https://huggingface.co/klusai/tf2-12b-gguf) (15k EN→RO fables, GPT-o3).
Compression: W8A8 (INT8 weights + INT8 activations) with LLM Compressor; channel-wise weight quant + dynamic per-token activation quant. ([VLLM Documentation][1])
Format: Published for Transformers with compressed tensors metadata; runs great on vLLM server. ([Hugging Face][2], [VLLM Documentation][3])
Hardware notes: INT8 execution supported on modern NVIDIA GPUs (compute capability ≥ 7.5; e.g., Turing/Ampere/Ada/Hopper). ([BookStack][4])

🚀 Inference

vLLM

pip install vllm

vllm serve tf2-12b-w8a8/ --dtype bfloat16 --tensor-parallel-size 1 --trust-remote-code --port 8000 --host 0.0.0.0

Then call it with your OpenAI Client (set base_url to your server).

✅ Intended Use

EN→RO machine translation of narrative prose (fables), educational localization, style-preserving story translation.

⚠️ Limitations

Domain-specific (fables); not tuned for legal/medical slang or highly technical text.
Synthetic training data may encode stylistic biases; human review recommended for production.

🔑 License

This repository: MIT
Use must also comply with the Gemma base model license.

📝 Changelog

v1.0 (W8A8): LoRA-merged, quantized with LLM Compressor to W8A8; uploaded with compressed-tensors metadata for Transformers & vLLM. ([VLLM Documentation][5])

Downloads last month: 3

Safetensors

Model size

12B params

Tensor type

BF16

F8_E4M3