Instructions to use anirvankrishna/TaskB_Full_Finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anirvankrishna/TaskB_Full_Finetune with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="anirvankrishna/TaskB_Full_Finetune")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("anirvankrishna/TaskB_Full_Finetune") model = AutoModelForCausalLM.from_pretrained("anirvankrishna/TaskB_Full_Finetune", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from anirvankrishna/TaskB_Full_Finetune: direct link, hf CLI and curl.
- Browser
- Download file 297 Bytes
-
https://huggingface.co/anirvankrishna/TaskB_Full_Finetune/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://anirvankrishna/TaskB_Full_Finetune/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/anirvankrishna/TaskB_Full_Finetune/resolve/main/tokenizer_config.json
297 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<|endoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "errors": "replace", | |
| "is_local": false, | |
| "model_max_length": 1024, | |
| "pad_token": "<|endoftext|>", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "<|endoftext|>" | |
| } | |