42 lines
917 B
JSON
42 lines
917 B
JSON
|
{
|
||
|
|
"_name_or_path": "/workspace/output_v2",
|
||
|
|
"architectures": [
|
||
|
|
"Mamba2ForCausalLM"
|
||
|
|
],
|
||
|
|
"bos_token_id": null,
|
||
|
|
"chunk_size": 256,
|
||
|
|
"conv_kernel": 4,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 248046,
|
||
|
|
"expand": 2,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 1024,
|
||
|
|
"initializer_range": 0.1,
|
||
|
|
"layer_norm_epsilon": 1e-05,
|
||
|
|
"model_type": "mamba2",
|
||
|
|
"n_groups": 1,
|
||
|
|
"num_heads": 32,
|
||
|
|
"num_hidden_layers": 48,
|
||
|
|
"pad_token_id": 248044,
|
||
|
|
"rescale_prenorm_residual": false,
|
||
|
|
"residual_in_fp32": true,
|
||
|
|
"rms_norm": true,
|
||
|
|
"state_size": 128,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"time_step_floor": 0.0001,
|
||
|
|
"time_step_limit": [
|
||
|
|
0.0,
|
||
|
|
3.4028235e+38
|
||
|
|
],
|
||
|
|
"time_step_max": 0.1,
|
||
|
|
"time_step_min": 0.001,
|
||
|
|
"time_step_rank": 256,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.46.3",
|
||
|
|
"use_bias": false,
|
||
|
|
"use_cache": false,
|
||
|
|
"use_conv_bias": true,
|
||
|
|
"vocab_size": 248077
|
||
|
|
}
|