Instructions to use ucla-cmllab/llama-3-qlora-ultrachat-200k-processed-indicator-0.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ucla-cmllab/llama-3-qlora-ultrachat-200k-processed-indicator-0.6 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
|
@@ -2068,6 +2068,7 @@
|
|
| 2068 |
"bos_token": "<|begin_of_text|>",
|
| 2069 |
"clean_up_tokenization_spaces": true,
|
| 2070 |
"eos_token": "<|end_of_text|>",
|
|
|
|
| 2071 |
"model_input_names": [
|
| 2072 |
"input_ids",
|
| 2073 |
"attention_mask"
|
|
|
|
| 2068 |
"bos_token": "<|begin_of_text|>",
|
| 2069 |
"clean_up_tokenization_spaces": true,
|
| 2070 |
"eos_token": "<|end_of_text|>",
|
| 2071 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 2072 |
"model_input_names": [
|
| 2073 |
"input_ids",
|
| 2074 |
"attention_mask"
|