deepframe-vllm / config.json
sdio-vincent's picture
Release main
81496a7 verified
{
"architectures": [
"DeepFrameForConditionalGeneration"
],
"audio_config": {
"activation_dropout": 0.0,
"activation_function": "gelu",
"attention_dropout": 0.0,
"d_model": 1280,
"dropout": 0.0,
"dtype": "bfloat16",
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"init_std": 0.02,
"max_source_positions": 1500,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"qformer_config": {
"_name_or_path": "",
"add_cross_attention": true,
"architectures": null,
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_freq": 1,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dtype": null,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_width": 1280,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 3072,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 12288,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 2,
"num_return_sequences": 1,
"out_hidden_size": 4096,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"query_length": 1,
"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,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 30522
},
"scale_embedding": false,
"second_per_window": 0.5,
"second_stride": 0.5,
"use_cache": true
},
"audio_end_token_id": 151671,
"audio_start_token_id": 151669,
"audio_token_id": 151670,
"dtype": "bfloat16",
"eos_token_id": 151645,
"image_token_id": 151655,
"model_type": "qwen3_vl_audio",
"pad_token_id": 151643,
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 262144,
"model_type": "qwen3_vl_text",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_type": "default"
},
"rope_theta": 5000000,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 151672
},
"tie_word_embeddings": false,
"transformers_version": "4.57.3",
"use_cache": true,
"video_token_id": 151656,
"vision_config": {
"deepstack_visual_indexes": [
8,
16,
24
],
"depth": 27,
"dtype": "bfloat16",
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_vl",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 4096,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2,
"tokens_per_second": 4,
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"_original_model_type": "qwen3_vl_audio",
"_original_architectures": [
"VideoSALMONN2_Qwen3"
]
}