Instructions to use thnhan3/sft_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thnhan3/sft_model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="thnhan3/sft_model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("thnhan3/sft_model") model = AutoModelForSeq2SeqLM.from_pretrained("thnhan3/sft_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from thnhan3/sft_model: direct link, hf CLI and curl.
- Browser
- Download file 726 Bytes
-
https://huggingface.co/thnhan3/sft_model/resolve/main/config.json
- Command line
-
hf download hf://thnhan3/sft_model/config.json
-
curl -L -o config.json https://huggingface.co/thnhan3/sft_model/resolve/main/config.json
726 Bytes
| { | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 3072, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "relu", | |
| "dropout_rate": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "relu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": false, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "transformers_version": "4.57.1", | |
| "use_cache": false, | |
| "vocab_size": 36096 | |
| } | |