| { | |
| "activation_checkpoint_impl": "per-iteration", | |
| "architecture_class_name": "RecurrentGPT", | |
| "architectures": [ | |
| "RavenForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "raven_config_minimal.RavenConfig", | |
| "AutoModelForCausalLM": "raven_modeling_minimal.RavenForCausalLM" | |
| }, | |
| "bias": false, | |
| "block_class_name": "SandwichBlock", | |
| "block_size": 4096, | |
| "effective_expected_depth": 132, | |
| "head_dim": 96, | |
| "init_orthogonal": false, | |
| "init_strategy": "takase", | |
| "init_values": { | |
| "embed_scale": 72.6636084983398, | |
| "embedding": 0.008703882797784892, | |
| "out_proj": 0.0005356869554443541, | |
| "std": 0.008703882797784892 | |
| }, | |
| "injection_type": "linear", | |
| "intermediate_size": 17920, | |
| "mean_backprop_depth": 8, | |
| "mean_recurrence": 32, | |
| "mlp_class_name": "GatedMLP", | |
| "model_type": "huginn_raven", | |
| "n_embd": 5280, | |
| "n_heads": 55, | |
| "n_layers": 8, | |
| "n_layers_in_coda": 2, | |
| "n_layers_in_prelude": 2, | |
| "n_layers_in_recurrent_block": 4, | |
| "nonlin_name": "SiLU", | |
| "norm_class_name": "RMSNorm_llama", | |
| "norm_eps": 1e-06, | |
| "num_key_value_heads": 55, | |
| "padded_vocab_size": 65536, | |
| "padding_multiple": 4096, | |
| "qk_bias": true, | |
| "rope_base": 50000, | |
| "sampling_scheme": "poisson-lognormal-filling", | |
| "state_init": "like-init", | |
| "tie_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "vocab_size": 65536 | |
| } | |