{ "_name_or_path": "../logs/v76-34kdataset-512k-bs343-2te-69k-bs10-170k-768-cd0.02-72k-rebal2-w-te-cd0.001-20240813-211610/ckpts/rolling-v76-34kdataset-512k-bs343-2te-69k-bs10-170k-768-cd0.02-72k-rebal2-w-te-cd0.001-ep04-gs36835/text_encoder", "architectures": [ "CLIPTextModel" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "eos_token_id": 2, "hidden_act": "gelu", "hidden_size": 1024, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "num_attention_heads": 16, "num_hidden_layers": 23, "pad_token_id": 1, "projection_dim": 512, "torch_dtype": "float16", "transformers_version": "4.42.3", "vocab_size": 49408 }