Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use israel/gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use israel/gemma with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="israel/gemma") 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("israel/gemma") model = AutoModelForCausalLM.from_pretrained("israel/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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use israel/gemma with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "israel/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": "israel/gemma", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/israel/gemma
- SGLang
How to use israel/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 "israel/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": "israel/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 "israel/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": "israel/gemma", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use israel/gemma with Docker Model Runner:
docker model run hf.co/israel/gemma
Download trainer_log.jsonl from israel/gemma: direct link, hf CLI and curl.
- Browser
- Download file 527 Bytes
-
https://huggingface.co/israel/gemma/resolve/main/trainer_log.jsonl
- Command line
-
hf download hf://israel/gemma/trainer_log.jsonl
-
curl -L -o trainer_log.jsonl https://huggingface.co/israel/gemma/resolve/main/trainer_log.jsonl
527 Bytes
| {"current_steps": 1000, "total_steps": 2860, "loss": 0.4662, "lr": 8.223278112677121e-06, "epoch": 1.749234135667396, "percentage": 34.97, "elapsed_time": "3:20:05", "remaining_time": "6:12:09"} | |
| {"current_steps": 2000, "total_steps": 2860, "loss": 0.1906, "lr": 2.5158716126030835e-06, "epoch": 3.497155361050328, "percentage": 69.93, "elapsed_time": "6:39:55", "remaining_time": "2:51:58"} | |
| {"current_steps": 2860, "total_steps": 2860, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "9:32:43", "remaining_time": "0:00:00"} | |