Text Generation
Transformers
TensorBoard
Safetensors
gemma3_text
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use seyhankokcu/functiongemma-270m-it-simple-tool-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seyhankokcu/functiongemma-270m-it-simple-tool-calling with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="seyhankokcu/functiongemma-270m-it-simple-tool-calling") 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("seyhankokcu/functiongemma-270m-it-simple-tool-calling") model = AutoModelForCausalLM.from_pretrained("seyhankokcu/functiongemma-270m-it-simple-tool-calling", 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 seyhankokcu/functiongemma-270m-it-simple-tool-calling with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "seyhankokcu/functiongemma-270m-it-simple-tool-calling" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "seyhankokcu/functiongemma-270m-it-simple-tool-calling", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/seyhankokcu/functiongemma-270m-it-simple-tool-calling
- SGLang
How to use seyhankokcu/functiongemma-270m-it-simple-tool-calling 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 "seyhankokcu/functiongemma-270m-it-simple-tool-calling" \ --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": "seyhankokcu/functiongemma-270m-it-simple-tool-calling", "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 "seyhankokcu/functiongemma-270m-it-simple-tool-calling" \ --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": "seyhankokcu/functiongemma-270m-it-simple-tool-calling", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use seyhankokcu/functiongemma-270m-it-simple-tool-calling with Docker Model Runner:
docker model run hf.co/seyhankokcu/functiongemma-270m-it-simple-tool-calling
Commit History
-
Training in progress, step 80
Verified signature82123e5 -
Training in progress, step 40
Verified signature267347b -
Model save
Verified signature7beb048 -
Training in progress, epoch 7
Verified signature8837729 -
Training in progress, epoch 5
Verified signature060c49e -
Training in progress, epoch 3
Verified signaturec736785 -
Training in progress, epoch 1
Verified signaturee5b9573 -
Training in progress, step 264
Verified signaturee73e021 -
Training in progress, step 264
Verified signature4feef4a -
Training in progress, step 264
Verified signature3b9fbd1 -
Model save
Verified signature90429a8 -
Training in progress, step 500
Verified signature62e68e3 -
Training in progress, step 264
Verified signature37bf9e7
-
Training in progress, step 3968
Verified signature1706f04 -
Training in progress, step 3500
Verified signature200cbc9 -
Training in progress, step 3000
Verified signature6745360 -
Training in progress, step 2500
Verified signature25c98ee -
Training in progress, step 2000
Verified signature8abfb0d -
Training in progress, step 1500
Verified signatured5d5189 -
Training in progress, step 1000
Verified signatureff24dca -
Training in progress, step 500
Verified signatureff9d3ef -
Training in progress, step 4040
Verified signaturee3569af -
Training in progress, step 4000
Verified signature94a5e70 -
Training in progress, step 3500
Verified signature67dc5d5 -
Training in progress, step 3000
Verified signature84db1dd -
Training in progress, step 2500
Verified signature53c3c5e -
Training in progress, step 2000
Verified signature6f8dc47 -
Training in progress, step 1500
Verified signature1b20a11 -
Training in progress, step 1000
Verified signaturefbfcac2 -
Training in progress, step 500
Verified signature7515850 -
Training in progress, step 976
Verified signaturef551cfe -
Training in progress, step 500
Verified signaturecea2f77 -
Training in progress, step 500
Verified signatured0707ef -
Training in progress, step 171
Verified signature3ef422e -
Training in progress, step 1350
Verified signature957aaba -
Training in progress, step 1000
Verified signature7f65be0 -
Training in progress, step 500
Verified signatureef3194e -
Training in progress, step 500
Verified signatureb9b7d23 -
Training in progress, step 96
Verified signature5112271 -
Training in progress, step 72
Verified signature2e0fcd3 -
Training in progress, step 72
Verified signaturec810e9d -
Training in progress, step 64
Verified signature5bfd1cd -
Training in progress, step 64
Verified signature3ae481b -
Training in progress, step 40
Verified signature64c2019 -
initial commit
Verified signaturee2d67a7