Text Generation
Transformers
Safetensors
English
gemma3_text
text-generation-inference
unsloth
conversational
Instructions to use while1/gemma3-1b-it-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use while1/gemma3-1b-it-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="while1/gemma3-1b-it-ft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("while1/gemma3-1b-it-ft") model = AutoModelForCausalLM.from_pretrained("while1/gemma3-1b-it-ft", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use while1/gemma3-1b-it-ft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "while1/gemma3-1b-it-ft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "while1/gemma3-1b-it-ft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/while1/gemma3-1b-it-ft
- SGLang
How to use while1/gemma3-1b-it-ft 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 "while1/gemma3-1b-it-ft" \ --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": "while1/gemma3-1b-it-ft", "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 "while1/gemma3-1b-it-ft" \ --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": "while1/gemma3-1b-it-ft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use while1/gemma3-1b-it-ft with Docker Model Runner:
docker model run hf.co/while1/gemma3-1b-it-ft
Commit History
-
(Trained with Unsloth)
Verified signature9bd91f0 -
(Trained with Unsloth)
Verified signature8f0d7ab -
Unsloth Model Card
Verified signature782ba27 -
Training in progress, step 558, checkpoint
Verified signaturebdd87b0 -
Training in progress, step 558
Verified signatured2fa653 -
Training in progress, step 550, checkpoint
Verified signature2745e8e -
Training in progress, step 550
Verified signature6c0dbc2 -
Training in progress, step 500, checkpoint
Verified signaturec91bd17 -
Training in progress, step 500
Verified signature3109f86 -
Training in progress, step 450, checkpoint
Verified signature7ca2729 -
Training in progress, step 450
Verified signature12c0ddf -
Training in progress, step 400, checkpoint
Verified signaturee869415 -
Training in progress, step 400
Verified signatureb3a2042 -
Training in progress, step 350, checkpoint
Verified signature174492b -
Training in progress, step 350
Verified signaturec8c4ab0 -
Training in progress, step 300, checkpoint
Verified signature48291a3 -
Training in progress, step 300
Verified signature6ae08bc -
Training in progress, step 250, checkpoint
Verified signature64ad2aa -
Training in progress, step 250
Verified signaturef6beb46 -
Training in progress, step 200, checkpoint
Verified signaturedb008fb -
Training in progress, step 200
Verified signatureb7aab35 -
Training in progress, step 150, checkpoint
Verified signatureaa117b1 -
Training in progress, step 150
Verified signature4c2b721 -
Training in progress, step 100, checkpoint
Verified signature7cb76fb -
Training in progress, step 100
Verified signaturebd6e4db -
Training in progress, step 50, checkpoint
Verified signatureb51f9ee -
Training in progress, step 50
Verified signatureaf1e575
-
Training in progress, step 150
Verified signaturef9c68b2 -
Training in progress, step 100
Verified signaturea60f3e7 -
Training in progress, step 50
Verified signature9d471e3 -
initial commit
Verified signature1b5e997