| { | |
| "activation_function": "swiglu", | |
| "architectures": [ | |
| "JAISLMHeadModel" | |
| ], | |
| "attn_pdrop": 0.0, | |
| "bos_token_id": 0, | |
| "embd_pdrop": 0.0, | |
| "embeddings_scale": 14.6, | |
| "eos_token_id": 0, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "jais", | |
| "n_embd": 32, | |
| "n_head": 2, | |
| "n_inner": 42, | |
| "n_layer": 2, | |
| "n_positions": 128, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "alibi", | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.0, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "scale_qk_dot_by_d": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "vocab_size": 84992, | |
| "width_scale": 0.11100000000000002 | |
| } | |