Instructions to use Lambent/Fabled-Gemma4-31B-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lambent/Fabled-Gemma4-31B-Adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it")
model = PeftModel.from_pretrained(base_model, "Lambent/Fabled-Gemma4-31B-Adapter")

Transformers

How to use Lambent/Fabled-Gemma4-31B-Adapter with Transformers:

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

pipe = pipeline("text-generation", model="Lambent/Fabled-Gemma4-31B-Adapter")
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("Lambent/Fabled-Gemma4-31B-Adapter")
model = AutoModelForImageTextToText.from_pretrained("Lambent/Fabled-Gemma4-31B-Adapter")
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 Lambent/Fabled-Gemma4-31B-Adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lambent/Fabled-Gemma4-31B-Adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lambent/Fabled-Gemma4-31B-Adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Lambent/Fabled-Gemma4-31B-Adapter

SGLang

How to use Lambent/Fabled-Gemma4-31B-Adapter 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 "Lambent/Fabled-Gemma4-31B-Adapter" \
    --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": "Lambent/Fabled-Gemma4-31B-Adapter",
		"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 "Lambent/Fabled-Gemma4-31B-Adapter" \
        --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": "Lambent/Fabled-Gemma4-31B-Adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Lambent/Fabled-Gemma4-31B-Adapter with Docker Model Runner:
```
docker model run hf.co/Lambent/Fabled-Gemma4-31B-Adapter
```

See axolotl config

axolotl version: 0.16.0.dev0

base_model: google/gemma-4-31B-it

# plugins:
#   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
#   - axolotl.integrations.liger.LigerPlugin
# torch_compile: true
# liger_layer_norm: true
# liger_rope: true
# liger_rms_norm: true
# liger_glu_activation: true
# liger_rms_norm_gated: true
strict: false

chat_template: gemma4
eot_tokens:
  - "<turn|>"
datasets:
  - path: Lambent/fable-conversations-memory-gemma-8k
    type: chat_template
    split: train
  - path: Lambent/fable-distilled-memory-gemma-8k
    type: chat_template
    split: train
output_dir: ./outputs/fabled-gemma4-31b-qlora-blackwell

sequence_len: 9216
sample_packing: true
train_on_inputs: true

load_in_4bit: true
adapter: qlora
lora_r: 256
lora_alpha: 256
lora_dropout: 0

# Restrict LoRA to text backbone only (skip vision/audio encoders)
lora_target_modules: 'model.language_model.layers.[\d]+.(_checkpoint_wrapped_module.)?(mlp|self_attn).(up|down|gate|q|k|v|o)_proj'

lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

bnb_config_kwargs:
  bnb_4bit_use_double_quant: true

wandb_project: fabled
wandb_entity:
wandb_watch:
wandb_name: gemma4-31b-qlora-blackwell-sdpa
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-6

bf16: auto
tf32: true

gradient_checkpointing: true
logging_steps: 1

sdp_attention: true

warmup_ratio: 0.1
saves_per_epoch: 4
weight_decay: 0.0
special_tokens:

outputs/fabled-gemma4-31b-qlora-blackwell

This model is a fine-tuned version of google/gemma-4-31B-it on the Lambent/fable-conversations-memory-gemma-8k and the Lambent/fable-distilled-memory-gemma-8k datasets.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 244
training_steps: 2445

Training results

Framework versions

PEFT 0.18.1
Transformers 5.5.0
Pytorch 2.10.0+cu128
Datasets 4.8.4
Tokenizers 0.22.2

Downloads last month: 20

Model tree for Lambent/Fabled-Gemma4-31B-Adapter

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Adapter

(98)

this model