| { |
| "architectures": [ |
| "T5EncoderModel" |
| ], |
| "classifier_dropout": 0.0, |
| "d_ff": 10240, |
| "d_kv": 64, |
| "d_model": 4096, |
| "decoder_start_token_id": 0, |
| "dense_act_fn": "gelu_new", |
| "dropout_rate": 0.1, |
| "eos_token_id": 1, |
| "feed_forward_proj": "gated-gelu", |
| "initializer_factor": 1.0, |
| "is_encoder_decoder": true, |
| "is_gated_act": true, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "t5", |
| "num_decoder_layers": 24, |
| "num_heads": 64, |
| "num_layers": 24, |
| "output_past": true, |
| "pad_token_id": 0, |
| "quantization_config": { |
| "modules_to_not_convert": null, |
| "quant_method": "torchao", |
| "quant_type": { |
| "default": { |
| "_data": { |
| "set_inductor_config": true, |
| "weight_dtype": { |
| "_data": "float8_e4m3fn", |
| "_type": "torch.dtype" |
| } |
| }, |
| "_type": "Float8WeightOnlyConfig", |
| "_version": 1 |
| } |
| }, |
| "quant_type_kwargs": {} |
| }, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 32128 |
| } |
|
|
