Instructions to use VoErik/cypher-gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VoErik/cypher-gemma with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VoErik/cypher-gemma")
model = AutoModelForCausalLM.from_pretrained("VoErik/cypher-gemma", 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 VoErik/cypher-gemma with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/VoErik/cypher-gemma

SGLang

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

Docker Model Runner
How to use VoErik/cypher-gemma with Docker Model Runner:
```
docker model run hf.co/VoErik/cypher-gemma
```

VoErik commited on Oct 10, 2025

Commit

47e0114

verified ·

1 Parent(s): a81ce7e

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -12

README.md CHANGED Viewed

@@ -1,36 +1,43 @@
 ---
 base_model: google/gemma-3-270m-it
 library_name: transformers
-model_name: checkpoints
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license
 ---
-# Model Card for checkpoints
-This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ```python
 from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="VoErik/checkpoints", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 ## Training procedure
-This model was trained with SFT.
 ### Framework versions
@@ -42,8 +49,6 @@ This model was trained with SFT.
 ## Citations
 Cite TRL as:
 ```bibtex

 ---
 base_model: google/gemma-3-270m-it
 library_name: transformers
+model_name: cypher-gemma
 tags:
 - generated_from_trainer
 - trl
 - sft
+- cypher
 licence: license
+datasets:
+- neo4j/text2cypher-2025v1
+pipeline_tag: text-generation
+language:
+- en
 ---
+# Model Card
+This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it). Its purpose is turning natural language queries into CypherQueryLanguage.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ```python
 from transformers import pipeline
+from schemas import MOVIE_SCHEMA # you need to define this yourself!
+query = "Which actors played a role in the movie Titanic?"
+pipe = pipeline("text-generation", model="VoErik/cypher-gemma", device="cuda")
+output = pipe([{"role": "user", "content": f"Question: {question} \n Schema: {MOVIE_SCHEMA}"}], max_new_tokens=256, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 ## Training procedure
+This model was trained with SFT on the text2cypher-2025v1 dataset from Neo4j.
+It was trained for roughly 3500 steps.
 ### Framework versions
 ## Citations
 Cite TRL as:
 ```bibtex