|
{ |
|
"_attn_implementation_autoset": false, |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"Llama4ForConditionalGeneration" |
|
], |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"boi_token_index": 200080, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eoi_token_index": 200081, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"image_token_index": 200092, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "llama4", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"quantization": { |
|
"group_size": 64, |
|
"bits": 4 |
|
}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"text_config": { |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"output_attentions": false, |
|
"torchscript": false, |
|
"torch_dtype": "bfloat16", |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": false, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": false, |
|
"is_decoder": false, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": false, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": null, |
|
"finetuning_task": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"tokenizer_class": null, |
|
"prefix": null, |
|
"bos_token_id": 200000, |
|
"pad_token_id": 200018, |
|
"eos_token_id": [ |
|
200001, |
|
200007, |
|
200008 |
|
], |
|
"sep_token_id": null, |
|
"decoder_start_token_id": null, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "", |
|
"_attn_implementation_autoset": true, |
|
"attention_bias": false, |
|
"for_llm_compressor": false, |
|
"model_type": "llama4_text", |
|
"attn_temperature_tuning": 4, |
|
"attn_scale": 0.1, |
|
"floor_scale": 8192, |
|
"vocab_size": 202048, |
|
"max_position_embeddings": 10485760, |
|
"hidden_size": 5120, |
|
"intermediate_size": 8192, |
|
"intermediate_size_mlp": 16384, |
|
"num_hidden_layers": 48, |
|
"num_attention_heads": 40, |
|
"rope_scaling": { |
|
"factor": 16.0, |
|
"high_freq_factor": 1.0, |
|
"low_freq_factor": 1.0, |
|
"original_max_position_embeddings": 8192, |
|
"rope_type": "llama3" |
|
}, |
|
"num_key_value_heads": 8, |
|
"hidden_act": "silu", |
|
"initializer_range": 0.02, |
|
"rms_norm_eps": 1e-05, |
|
"use_cache": true, |
|
"rope_theta": 500000.0, |
|
"attention_dropout": 0.0, |
|
"head_dim": 128, |
|
"use_qk_norm": true, |
|
"num_experts_per_tok": 1, |
|
"num_local_experts": 16, |
|
"output_router_logits": false, |
|
"router_aux_loss_coef": 0.001, |
|
"router_jitter_noise": 0.0, |
|
"no_rope_layers": [ |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0, |
|
1, |
|
1, |
|
1, |
|
0 |
|
], |
|
"interleave_moe_layer_step": 1, |
|
"moe_layers": [ |
|
0, |
|
1, |
|
2, |
|
3, |
|
4, |
|
5, |
|
6, |
|
7, |
|
8, |
|
9, |
|
10, |
|
11, |
|
12, |
|
13, |
|
14, |
|
15, |
|
16, |
|
17, |
|
18, |
|
19, |
|
20, |
|
21, |
|
22, |
|
23, |
|
24, |
|
25, |
|
26, |
|
27, |
|
28, |
|
29, |
|
30, |
|
31, |
|
32, |
|
33, |
|
34, |
|
35, |
|
36, |
|
37, |
|
38, |
|
39, |
|
40, |
|
41, |
|
42, |
|
43, |
|
44, |
|
45, |
|
46, |
|
47 |
|
], |
|
"attention_chunk_size": 8192 |
|
}, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": false, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": "bfloat16", |
|
"torchscript": false, |
|
"transformers_version": "4.51.0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"vision_config": { |
|
"hidden_size": 1408, |
|
"hidden_act": "gelu", |
|
"num_hidden_layers": 34, |
|
"num_channels": 3, |
|
"intermediate_size": 5632, |
|
"image_size": 336, |
|
"vision_output_dim": 4096, |
|
"patch_size": 14, |
|
"norm_eps": 1e-05, |
|
"num_attention_heads": 16, |
|
"initializer_range": 0.02, |
|
"pixel_shuffle_ratio": 0.5, |
|
"projector_input_dim": 4096, |
|
"projector_output_dim": 4096, |
|
"multi_modal_projector_bias": false, |
|
"projector_dropout": 0.0, |
|
"attention_dropout": 0.0, |
|
"vision_feature_layer": -1, |
|
"vision_feature_select_strategy": "default", |
|
"rope_theta": 10000, |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"output_attentions": false, |
|
"torchscript": false, |
|
"torch_dtype": null, |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": true, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": false, |
|
"is_decoder": false, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": false, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": false, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": null, |
|
"finetuning_task": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"tokenizer_class": null, |
|
"prefix": null, |
|
"bos_token_id": null, |
|
"pad_token_id": null, |
|
"eos_token_id": null, |
|
"sep_token_id": null, |
|
"decoder_start_token_id": null, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "", |
|
"_attn_implementation_autoset": true, |
|
"model_type": "llama4_vision_model" |
|
} |
|
} |