Instructions to use Interact-ai/interact-ai-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Interact-ai/interact-ai-12b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-12b-it")
model = PeftModel.from_pretrained(base_model, "Interact-ai/interact-ai-12b")

Transformers

How to use Interact-ai/interact-ai-12b with Transformers:

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

pipe = pipeline("text-generation", model="Interact-ai/interact-ai-12b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Interact-ai/interact-ai-12b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Interact-ai/interact-ai-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Interact-ai/interact-ai-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": "Interact-ai/interact-ai-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Interact-ai/interact-ai-12b

SGLang

How to use Interact-ai/interact-ai-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 "Interact-ai/interact-ai-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": "Interact-ai/interact-ai-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 "Interact-ai/interact-ai-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": "Interact-ai/interact-ai-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Interact-ai/interact-ai-12b with Docker Model Runner:
```
docker model run hf.co/Interact-ai/interact-ai-12b
```

Interact AI 12B Coder

Interact AI 12B Coder is an Interact AI coding adapter built on Google's google/gemma-3-12b-it. It is distributed as a LoRA/PEFT adapter and requires the base model for inference. This repository does not contain the full 12B parameter base model.

Model details

Developed and shared by: Interact AI
Model type: LoRA/PEFT adapter for a causal language model
Base model: google/gemma-3-12b-it
Intended use: Coding-focused text generation
Language(s): To be documented
Adapter format: Safetensors
PEFT version: 0.21.2
License: To be documented for this adapter; Google's Gemma Terms of Use apply to the base model

Usage

Load the adapter together with the Gemma base model using Transformers and PEFT:

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model_path = "Interact AI 12B"
model = AutoPeftModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

The adapter is not a standalone model. The base model must be available and its terms of use must be followed.

Training

The adapter was fine-tuned from google/gemma-3-12b-it using LoRA. The training dataset, data-processing procedure, precision, schedule, and compute details are not yet documented.

Evaluation and limitations

No benchmark results or safety evaluations have been provided. Outputs may be inaccurate, incomplete, biased, or insecure. Evaluate generated code before execution and do not use the model for safety-critical or high-impact decisions without appropriate validation.

Attribution

Interact AI 12B Coder is an adapter developed by Interact AI. The underlying Gemma 3 12B model is developed by Google DeepMind. This adapter should not be represented as the original Google Gemma model.

Model card authors

Interact AI

Framework versions

PEFT 0.21.2

Downloads last month: 25

Model tree for Interact-ai/interact-ai-12b

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Adapter

(431)

this model

Interact-ai
/

interact-ai-12b