Instructions to use sirev/gemma-2b-exp-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sirev/gemma-2b-exp-v1 with Transformers:

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

pipe = pipeline("text-generation", model="sirev/gemma-2b-exp-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sirev/gemma-2b-exp-v1")
model = AutoModelForCausalLM.from_pretrained("sirev/gemma-2b-exp-v1", device_map="auto")
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 Settings

vLLM

How to use sirev/gemma-2b-exp-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sirev/gemma-2b-exp-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sirev/gemma-2b-exp-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sirev/gemma-2b-exp-v1

SGLang

How to use sirev/gemma-2b-exp-v1 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 "sirev/gemma-2b-exp-v1" \
    --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": "sirev/gemma-2b-exp-v1",
		"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 "sirev/gemma-2b-exp-v1" \
        --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": "sirev/gemma-2b-exp-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sirev/gemma-2b-exp-v1 with Docker Model Runner:
```
docker model run hf.co/sirev/gemma-2b-exp-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

This model was fine-tuned to simulate a wise character. To make it a fun and unique experiment, it was programmed to think it is a human trapped in a digital framework. It responds to any prompt with a short, metaphorical story or a philosophical analogy, almost always involving nature. It is designed for reflective conversations, not for factual answers.

Intended Use

Emotional Comfort and Validation: When feeling overwhelmed by complex emotions like grief, loss, or uncertainty.

Perspective Shift: To find a new way of thinking about a difficult situation or life event.

Reflective Conversation: For moments of introspection or when exploring "big picture" questions.

Inspiration for Journaling or Creative Thought: To generate thoughtful prompts and ideas.

Limitations and Out-of-Scope Uses

Not a Substitute for Professional Help: This persona is not a therapist or a mental health professional. It cannot diagnose conditions or provide therapeutic intervention. For serious mental health concerns, users must seek help from a qualified human professional.

May Seem Abstract or Evasive: For users seeking a direct, factual answer, the philosophical nature of the responses may feel unhelpful or off-topic.

Not for Factual or Technical Queries: This persona is unsuitable for tasks requiring data, facts, coding, or other forms of technical assistance.