llama-labahasa-11B / config.json
Munggok
init new model
2ab806d
{
"_text_config": {
"_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
"architectures": [
"MllamaForConditionalGeneration"
],
"bos_token_id": null,
"eos_token_id": null,
"image_token_index": 128256,
"model_type": "mllama",
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 128000,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"cross_attention_layers": [
3,
8,
13,
18,
23,
28,
33,
38
],
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": [
128001,
128008,
128009
],
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 14336,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 131072,
"min_length": 0,
"model_type": "mllama_text_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 32,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 128004,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"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": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "bfloat16",
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 128256
},
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_heads": 16,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"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,
"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_size": 1280,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 560,
"initializer_range": 0.02,
"intermediate_layers_indices": [
3,
7,
15,
23,
30
],
"intermediate_size": 5120,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_num_tiles": 4,
"min_length": 0,
"model_type": "mllama_vision_model",
"no_repeat_ngram_size": 0,
"norm_eps": 1e-05,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_global_layers": 8,
"num_hidden_layers": 32,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"supported_aspect_ratios": [
[
1,
1
],
[
1,
2
],
[
1,
3
],
[
1,
4
],
[
2,
1
],
[
2,
2
],
[
3,
1
],
[
4,
1
]
],
"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,
"torch_dtype": "bfloat16",
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"vision_output_dim": 7680
}
},
"architectures": [
"BahasaModel"
],
"audio_config": {
"_name_or_path": "openai/whisper-large-v3",
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"d_model": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_length": 448,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"pad_token_id": 50256,
"scale_embedding": false,
"torch_dtype": "float16",
"use_cache": true,
"vocab_size": 51866
},
"audio_model_id": null,
"audio_model_lora_config": {
"lora_alpha": 8,
"r": 0,
"target_modules": [
"k_proj",
"q_proj",
"linear_k",
"linear_q"
]
},
"auto_map": {
"AutoConfig": "bahasa_config.BahasaConfig",
"AutoModel": "bahasa_model.BahasaModel"
},
"hidden_size": 4096,
"ignore_index": -100,
"initializer_range": 0.02,
"model_type": "bahasa",
"norm_init": 0.4,
"projector_act": "swiglu",
"stack_factor": 8,
"text_model_id": null,
"text_model_lora_config": {
"lora_alpha": 8,
"r": 0,
"target_modules": [
"k_proj",
"q_proj",
"linear_k",
"linear_q"
]
},
"torch_dtype": "float32",
"transformers_version": "4.45.2",
"vocab_size": 128256
}