136 lines
2.7 KiB
JSON
136 lines
2.7 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Llama4ForConditionalGeneration"
|
||
|
|
],
|
||
|
|
"boi_token_index": 200080,
|
||
|
|
"eoi_token_index": 200081,
|
||
|
|
"image_token_index": 200092,
|
||
|
|
"model_type": "llama4",
|
||
|
|
"text_config": {
|
||
|
|
"_attn_implementation_autoset": true,
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_chunk_size": null,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"attn_scale": 0.1,
|
||
|
|
"attn_temperature_tuning": true,
|
||
|
|
"bos_token_id": 200000,
|
||
|
|
"cache_implementation": "static",
|
||
|
|
"eos_token_id": [
|
||
|
|
200001,
|
||
|
|
200007,
|
||
|
|
200008
|
||
|
|
],
|
||
|
|
"floor_scale": 8192,
|
||
|
|
"for_llm_compressor": false,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"interleave_moe_layer_step": 0,
|
||
|
|
"intermediate_size": 8192,
|
||
|
|
"intermediate_size_mlp": 8192,
|
||
|
|
"max_position_embeddings": 10485760,
|
||
|
|
"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,
|
||
|
|
1,
|
||
|
|
1,
|
||
|
|
1,
|
||
|
|
1,
|
||
|
|
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": 40,
|
||
|
|
"num_experts_per_tok": 1,
|
||
|
|
"num_hidden_layers": 48,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"num_local_experts": 0,
|
||
|
|
"output_router_logits": false,
|
||
|
|
"pad_token_id": 200018,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 16,
|
||
|
|
"high_freq_factor": 1,
|
||
|
|
"low_freq_factor": 1.0,
|
||
|
|
"original_max_position_embeddings": 8192,
|
||
|
|
"rope_type": "llama3"
|
||
|
|
},
|
||
|
|
"rope_theta": 500000.0,
|
||
|
|
"router_aux_loss_coef": 0.001,
|
||
|
|
"router_jitter_noise": 0.0,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_qk_norm": true,
|
||
|
|
"vocab_size": 202048
|
||
|
|
},
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.52.0.dev0",
|
||
|
|
"vision_config": {
|
||
|
|
"_attn_implementation_autoset": true,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"hidden_act": "gelu",
|
||
|
|
"hidden_size": 1408,
|
||
|
|
"image_size": 336,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 5632,
|
||
|
|
"model_type": "llama4_vision_model",
|
||
|
|
"multi_modal_projector_bias": false,
|
||
|
|
"norm_eps": 1e-05,
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_channels": 3,
|
||
|
|
"num_hidden_layers": 34,
|
||
|
|
"patch_size": 14,
|
||
|
|
"pixel_shuffle_ratio": 0.5,
|
||
|
|
"projector_dropout": 0.0,
|
||
|
|
"projector_input_dim": 4096,
|
||
|
|
"projector_output_dim": 4096,
|
||
|
|
"rope_theta": 10000,
|
||
|
|
"vision_feature_layer": -1,
|
||
|
|
"vision_feature_select_strategy": "default",
|
||
|
|
"vision_output_dim": 4096
|
||
|
|
}
|
||
|
|
}
|