Instructions to use ToastyPigeon/g3-12b-it-unalign with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ToastyPigeon/g3-12b-it-unalign with Transformers:

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

pipe = pipeline("text-generation", model="ToastyPigeon/g3-12b-it-unalign")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ToastyPigeon/g3-12b-it-unalign")
model = AutoModelForCausalLM.from_pretrained("ToastyPigeon/g3-12b-it-unalign")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ToastyPigeon/g3-12b-it-unalign with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ToastyPigeon/g3-12b-it-unalign"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ToastyPigeon/g3-12b-it-unalign",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ToastyPigeon/g3-12b-it-unalign

SGLang

How to use ToastyPigeon/g3-12b-it-unalign 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 "ToastyPigeon/g3-12b-it-unalign" \
    --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": "ToastyPigeon/g3-12b-it-unalign",
		"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 "ToastyPigeon/g3-12b-it-unalign" \
        --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": "ToastyPigeon/g3-12b-it-unalign",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ToastyPigeon/g3-12b-it-unalign with Docker Model Runner:
```
docker model run hf.co/ToastyPigeon/g3-12b-it-unalign
```

g3-12b-it-unalign

This model is a fine-tuned version of unsloth/gemma-3-12b-it on the ToastyPigeon/unalign-v2 dataset. It achieves the following results on the evaluation set:

Loss: 1.4684

So, it seems alright. I noticed however that the responses got pretty short at the end of the 2nd epoch. Not like, unusably short, but generally shorter than I personally like.

The epoch 1 test gguf is based on this commit.

I personally prefer epoch 1 to epoch 2, and will likely update this or make a second proper commit for epoch 1.

Update: I did indeed make a second commit for the epoch 1 checkpoint.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 69
optimizer: Use apollo_adamw_layerwise with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
7.8965	0.0118	1	6.4897
4.4934	0.2	17	4.0497
3.9523	0.4	34	3.7484
3.5624	0.6	51	3.3152
2.7168	0.8	68	2.4773
2.1303	1.0	85	1.9483
1.8215	1.2	102	1.7577
1.7199	1.4	119	1.6561
1.5771	1.6	136	1.5611
1.5599	1.8	153	1.5124
1.4831	2.0	170	1.4684

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.4.1
Tokenizers 0.21.1

Downloads last month: 5

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for ToastyPigeon/g3-12b-it-unalign

Base model

google/gemma-3-12b-pt

Finetuned

unsloth/gemma-3-12b-it

Finetuned

(123)

this model