Instructions to use windgrin/c2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use windgrin/c2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data/LLM/Llama-3.2-11B-Vision-Instruct") model = PeftModel.from_pretrained(base_model, "windgrin/c2") - Notebooks
- Google Colab
- Kaggle
Download chat_template.json from windgrin/c2: direct link, hf CLI and curl.
- Browser
- Download file 558 Bytes
-
https://huggingface.co/windgrin/c2/resolve/main/chat_template.json
- Command line
-
hf download hf://windgrin/c2/chat_template.json
-
curl -L -o chat_template.json https://huggingface.co/windgrin/c2/resolve/main/chat_template.json
558 Bytes
| { | |
| "chat_template": "{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<|image|>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{ '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}" | |
| } | |