| { | |
| "architectures": [ | |
| "MambaForCausalLM" | |
| ], | |
| "bos_token_id": 0, | |
| "d_model": 2560, | |
| "eos_token_id": 0, | |
| "fused_add_norm": true, | |
| "hidden_size": 2560, | |
| "initializer_cfg": null, | |
| "model_type": "mamba", | |
| "n_layer": 64, | |
| "norm_epsilon": 1e-05, | |
| "pad_token_id": 0, | |
| "pad_vocab_size_multiple": 8, | |
| "residual_in_fp32": true, | |
| "rms_norm": true, | |
| "ssm_cfg": {}, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.3", | |
| "use_cache": true, | |
| "vocab_size": 50280 | |
| } | |