Instructions to use voidful/llmcodec-librispeech-abl-sa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use voidful/llmcodec-librispeech-abl-sa with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("voidful/llm-codec-abl-sa") model = PeftModel.from_pretrained(base_model, "voidful/llmcodec-librispeech-abl-sa") - Notebooks
- Google Colab
- Kaggle
Training completed: lora mode
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -327911,9 +327911,13 @@
|
|
| 327911 |
"eos_token": "<|im_end|>",
|
| 327912 |
"errors": "replace",
|
| 327913 |
"extra_special_tokens": {},
|
|
|
|
| 327914 |
"model_max_length": 1010000,
|
| 327915 |
"pad_token": "<|endoftext|>",
|
| 327916 |
"split_special_tokens": false,
|
|
|
|
| 327917 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
|
|
|
| 327918 |
"unk_token": null
|
| 327919 |
}
|
|
|
|
| 327911 |
"eos_token": "<|im_end|>",
|
| 327912 |
"errors": "replace",
|
| 327913 |
"extra_special_tokens": {},
|
| 327914 |
+
"max_length": 4096,
|
| 327915 |
"model_max_length": 1010000,
|
| 327916 |
"pad_token": "<|endoftext|>",
|
| 327917 |
"split_special_tokens": false,
|
| 327918 |
+
"stride": 0,
|
| 327919 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 327920 |
+
"truncation_side": "right",
|
| 327921 |
+
"truncation_strategy": "longest_first",
|
| 327922 |
"unk_token": null
|
| 327923 |
}
|