Instructions to use ClaudioItaly/FourFictionGemma-9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClaudioItaly/FourFictionGemma-9 with Transformers:

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

pipe = pipeline("text-generation", model="ClaudioItaly/FourFictionGemma-9")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ClaudioItaly/FourFictionGemma-9")
model = AutoModelForCausalLM.from_pretrained("ClaudioItaly/FourFictionGemma-9")
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 ClaudioItaly/FourFictionGemma-9 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClaudioItaly/FourFictionGemma-9"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClaudioItaly/FourFictionGemma-9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ClaudioItaly/FourFictionGemma-9

SGLang

How to use ClaudioItaly/FourFictionGemma-9 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 "ClaudioItaly/FourFictionGemma-9" \
    --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": "ClaudioItaly/FourFictionGemma-9",
		"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 "ClaudioItaly/FourFictionGemma-9" \
        --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": "ClaudioItaly/FourFictionGemma-9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ClaudioItaly/FourFictionGemma-9 with Docker Model Runner:
```
docker model run hf.co/ClaudioItaly/FourFictionGemma-9
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Modello GGUF https://huggingface.co/ClaudioItaly/FourFictionGemma-9-Q5_K_M-GGUF

merge

This is a merge of pre-trained language models created using mergekit. I created a fusion of 4 Gemma2 models specializing in storytelling and fictional writing. This pattern requires the GEMMA Instruct pattern. Responds very well to Prompts

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using ifable/gemma-2-Ifable-9B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/gemma2-gutenberg-9B
    parameters:
      density: 0.5
      weight: 0.5
  - model: lemon07r/Gemma-2-Ataraxy-9B
    parameters:
      density: 0.5
      weight: 0.5
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      density: 0.5
      weight: 0.5
merge_method: dare_ties
base_model: ifable/gemma-2-Ifable-9B
parameters:
  normalize: false
  int8_mask: true
dtype: float16