| { | |
| "architectures": [ | |
| "BambaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_layer_indices": [ | |
| 9, | |
| 18, | |
| 27 | |
| ], | |
| "attn_rotary_emb": 64, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "mamba_chunk_size": 256, | |
| "mamba_conv_bias": true, | |
| "mamba_d_conv": 4, | |
| "mamba_d_head": 64, | |
| "mamba_d_state": 128, | |
| "mamba_expand": 2, | |
| "mamba_n_groups": 1, | |
| "mamba_n_heads": 128, | |
| "mamba_proj_bias": false, | |
| "max_position_embeddings": 262144, | |
| "mlp_bias": false, | |
| "model_type": "bamba", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_logits_to_keep": 1, | |
| "pad_token_id": 0, | |
| "partial_rotary_factor": 0.5, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.52.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |