Instructions to use akkikiki/LLaDA-8B-Instruct-judge-fs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use akkikiki/LLaDA-8B-Instruct-judge-fs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="akkikiki/LLaDA-8B-Instruct-judge-fs", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("akkikiki/LLaDA-8B-Instruct-judge-fs", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload chat_template.jinja with huggingface_hub
Browse files- chat_template.jinja +5 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
| 2 |
+
|
| 3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
| 4 |
+
|
| 5 |
+
' }}
|