Text Classification
Transformers
Safetensors
Japanese
gemma2
text-generation
guardrail
safety
japanese
Instructions to use shibu-phys/arise-japanese-guardrail-gemma2b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shibu-phys/arise-japanese-guardrail-gemma2b-lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="shibu-phys/arise-japanese-guardrail-gemma2b-lora")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("shibu-phys/arise-japanese-guardrail-gemma2b-lora") model = AutoModelForCausalLM.from_pretrained("shibu-phys/arise-japanese-guardrail-gemma2b-lora") - Notebooks
- Google Colab
- Kaggle
| {{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + ' | |
| ' + message['content'] | trim + '<end_of_turn> | |
| ' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model | |
| '}}{% endif %} |