| { | |
| "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": 1024, | |
| "bos_token_id": 65504, | |
| "effective_expected_depth": 56, | |
| "eos_token_id": 65505, | |
| "head_dim": 64, | |
| "init_orthogonal": false, | |
| "init_strategy": "takase", | |
| "init_values": { | |
| "embed_scale": 1.0, | |
| "embedding": 0.008703882797784892, | |
| "out_proj": 0.0005356869554443541, | |
| "std": 0.008703882797784892 | |
| }, | |
| "injection_type": "linear", | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mean_backprop_depth": 8, | |
| "mean_recurrence": 8, | |
| "mlp_class_name": "GatedMLP", | |
| "model_type": "huginn_raven", | |
| "n_embd": 2048, | |
| "n_heads": 32, | |
| "n_layers": 14, | |
| "n_layers_in_coda": 4, | |
| "n_layers_in_prelude": 4, | |
| "n_layers_in_recurrent_block": 6, | |
| "nonlin_name": "SiLU", | |
| "norm_class_name": "RMSNorm_llama", | |
| "norm_eps": 1e-05, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 65509, | |
| "padded_vocab_size": 128256, | |
| "padding_multiple": 4096, | |
| "qk_bias": false, | |
| "rope_base": 500000.0, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "sampling_scheme": "poisson-lognormal-filling", | |
| "state_init": "like-init", | |
| "test_time_noise": 0, | |
| "test_time_noise_type": "fixed", | |
| "tie_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.1", | |
| "vocab_size": 128256 | |
| } |