| { | |
| "architectures": [ | |
| "BitMamba2LM" | |
| ], | |
| "model_type": "bitmamba", | |
| "d_model": 2048, | |
| "n_layers": 32, | |
| "n_heads": 32, | |
| "vocab_size": 50257, | |
| "ssm_d_state": 128, | |
| "ssm_d_conv": 4, | |
| "expand": 2, | |
| "rms_norm_eps": 1e-6, | |
| "quantization": { | |
| "bits": 1.58, | |
| "group_size": null, | |
| "zero_point": false | |
| }, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "transformers_version": "5.0.0" | |
| } | |