hf-transformers-bot's picture
Update tiny models for FalconH1Model
5eed2af verified
Raw
History Blame Contribute Delete
1.51 kB
{
"architectures": [
"FalconH1Model"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attention_in_multiplier": 1.0,
"attention_out_multiplier": 1.0,
"attn_layer_indices": [
1,
3
],
"attn_rotary_emb": 8,
"bos_token_id": 17,
"dtype": "float32",
"embedding_multiplier": 1.0,
"eos_token_id": 11,
"hidden_act": "silu",
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 64,
"key_multiplier": 1.0,
"lm_head_multiplier": 1.0,
"mamba_chunk_size": 16,
"mamba_conv_bias": true,
"mamba_d_conv": 4,
"mamba_d_head": 64,
"mamba_d_ssm": 1024,
"mamba_d_state": 16,
"mamba_expand": 2,
"mamba_n_groups": 1,
"mamba_n_heads": 16,
"mamba_norm_before_gate": true,
"mamba_proj_bias": false,
"mamba_rms_norm": false,
"max_position_embeddings": 512,
"mlp_bias": false,
"mlp_multipliers": [
1.0,
1.0
],
"model_type": "falcon_h1",
"num_attention_heads": 4,
"num_hidden_layers": 4,
"num_key_value_heads": 2,
"num_logits_to_keep": 1,
"pad_token_id": 65536,
"projectors_bias": false,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"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": false,
"time_step_limit": [
0.0,
{
"__float__": "Infinity"
}
],
"transformers_version": "5.16.0.dev0",
"use_cache": true,
"vocab_size": 65537
}