|
{ |
|
"_name_or_path": "fla-hub/mamba-1.3B-100B", |
|
"architectures": [ |
|
"MambaForCausalLM" |
|
], |
|
"bos_token_id": 0, |
|
"conv_kernel": 4, |
|
"eos_token_id": 0, |
|
"expand": 2, |
|
"fuse_cross_entropy": true, |
|
"fuse_norm": true, |
|
"hidden_act": "silu", |
|
"hidden_size": 2048, |
|
"initializer_range": 0.1, |
|
"intermediate_size": 4096, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "mamba", |
|
"num_hidden_layers": 48, |
|
"pad_token_id": null, |
|
"rescale_prenorm_residual": false, |
|
"residual_in_fp32": false, |
|
"state_size": 16, |
|
"tie_word_embeddings": true, |
|
"time_step_floor": 0.0001, |
|
"time_step_init_scheme": "random", |
|
"time_step_max": 0.1, |
|
"time_step_min": 0.001, |
|
"time_step_rank": 128, |
|
"time_step_scale": 1.0, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.39.3", |
|
"use_bias": false, |
|
"use_cache": true, |
|
"use_conv_bias": true, |
|
"vocab_size": 32000 |
|
} |
|
|