69 lines
1.5 KiB
JSON
69 lines
1.5 KiB
JSON
{
|
|
"architectures": [
|
|
"FalconH1ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attention_in_multiplier": 1.0,
|
|
"attention_out_multiplier": 1.0,
|
|
"bos_token_id": 1,
|
|
"dtype": "bfloat16",
|
|
"embedding_multiplier": 0.123046875,
|
|
"eos_token_id": 11,
|
|
"expansion_factor": 1.5,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 512,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 768,
|
|
"key_multiplier": 1.0,
|
|
"lm_head_multiplier": 0.078125,
|
|
"mamba_chunk_size": 128,
|
|
"mamba_conv_bias": true,
|
|
"mamba_d_conv": 4,
|
|
"mamba_d_head": 32,
|
|
"mamba_d_ssm": 768,
|
|
"mamba_d_state": 64,
|
|
"mamba_expand": 2,
|
|
"mamba_n_groups": 1,
|
|
"mamba_n_heads": 24,
|
|
"mamba_norm_before_gate": false,
|
|
"mamba_proj_bias": false,
|
|
"mamba_rms_norm": false,
|
|
"mamba_use_mlp": true,
|
|
"max_position_embeddings": 262144,
|
|
"mlp_bias": false,
|
|
"mlp_multipliers": [
|
|
1.0,
|
|
1.0
|
|
],
|
|
"model_type": "falcon_h1",
|
|
"num_attention_heads": 8,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 2,
|
|
"num_logits_to_keep": 1,
|
|
"pad_token_id": 0,
|
|
"projectors_bias": false,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 100000000000.0,
|
|
"sliding_window": null,
|
|
"ssm_in_multiplier": 1.0,
|
|
"ssm_multipliers": [
|
|
1.0,
|
|
1.0,
|
|
1.0,
|
|
1.0,
|
|
1.0
|
|
],
|
|
"ssm_out_multiplier": 1.0,
|
|
"tie_word_embeddings": true,
|
|
"time_step_floor": 0.0001,
|
|
"time_step_max": 0.1,
|
|
"time_step_min": 0.001,
|
|
"time_step_rank": "auto",
|
|
"transformers_version": "4.57.0",
|
|
"use_cache": true,
|
|
"vocab_size": 65536
|
|
}
|