Instructions to use ApocalypseParty/G4-31B-configQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApocalypseParty/G4-31B-configQA with Transformers:

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

pipe = pipeline("image-text-to-text", model="ApocalypseParty/G4-31B-configQA")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ApocalypseParty/G4-31B-configQA")
model = AutoModelForMultimodalLM.from_pretrained("ApocalypseParty/G4-31B-configQA")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ApocalypseParty/G4-31B-configQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApocalypseParty/G4-31B-configQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApocalypseParty/G4-31B-configQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ApocalypseParty/G4-31B-configQA

SGLang

How to use ApocalypseParty/G4-31B-configQA 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 "ApocalypseParty/G4-31B-configQA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApocalypseParty/G4-31B-configQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ApocalypseParty/G4-31B-configQA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApocalypseParty/G4-31B-configQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ApocalypseParty/G4-31B-configQA with Docker Model Runner:
```
docker model run hf.co/ApocalypseParty/G4-31B-configQA
```

G4-31B-configQA

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using google/gemma-4-31B-it as a base.

Models Merged

The following models were included in the merge:

ApocalypseParty/G4-31B-SFT-Diversity-1-5ep

Configuration

The following YAML configuration was used to produce this model:

merge_method: della_linear
base_model: google/gemma-4-31B-it
dtype: bfloat16
parameters:
  lambda: 1.0
  normalize: false
  rescale: false
  density: 1.0
models:
  - model: ApocalypseParty/G4-31B-SFT-Diversity-1-5ep
    parameters:
      weight:
        - filter: vision_tower
          value: 0.0
        - filter: embed_vision
          value: 0.0
        - filter: model.language_model.layers.5.self_attn
          value: 0.0
        - filter: model.language_model.layers.11.self_attn
          value: 0.0
        - filter: model.language_model.layers.17.self_attn
          value: 0.0
        - filter: model.language_model.layers.23.self_attn
          value: 0.0
        - filter: model.language_model.layers.29.self_attn
          value: 0.0
        - filter: model.language_model.layers.35.self_attn
          value: 0.0
        - filter: model.language_model.layers.41.self_attn
          value: 0.0
        - filter: model.language_model.layers.47.self_attn
          value: 0.0
        - filter: model.language_model.layers.53.self_attn
          value: 0.0
        - filter: model.language_model.layers.59.self_attn
          value: 0.0
        - value: 1.0