97 lines
1.8 KiB
JSON
97 lines
1.8 KiB
JSON
{
|
|
"architectures": [
|
|
"Llama4ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_chunk_size": 32768,
|
|
"attention_dropout": 0.0,
|
|
"attn_scale": 0.1,
|
|
"attn_temperature_tuning": false,
|
|
"bos_token_id": 128000,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": [
|
|
128001,
|
|
128008,
|
|
128009
|
|
],
|
|
"floor_scale": 8192,
|
|
"for_llm_compressor": false,
|
|
"head_dim": 64,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1536,
|
|
"initializer_range": 0.02,
|
|
"interleave_moe_layer_step": 0,
|
|
"intermediate_size": 8192,
|
|
"intermediate_size_mlp": 6144,
|
|
"layer_types": [
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention",
|
|
"full_attention"
|
|
],
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "llama4_text",
|
|
"moe_layers": [],
|
|
"no_rope_layers": [
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1
|
|
],
|
|
"num_attention_heads": 24,
|
|
"num_experts_per_tok": 0,
|
|
"num_hidden_layers": 22,
|
|
"num_key_value_heads": 6,
|
|
"num_local_experts": 0,
|
|
"output_router_logits": false,
|
|
"pad_token_id": null,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_parameters": {
|
|
"rope_theta": 8000000.0,
|
|
"rope_type": "default"
|
|
},
|
|
"router_aux_loss_coef": 0.001,
|
|
"router_jitter_noise": 0.0,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "5.2.0",
|
|
"use_cache": true,
|
|
"use_qk_norm": true,
|
|
"vocab_size": 128257
|
|
}
|