ahmed-masry's picture
Upload LlavaT5ForConditionalGeneration
91ae748 verified
{
"_name_or_path": "/content/flant5",
"architectures": [
"LlavaT5ForConditionalGeneration"
],
"auto_map": {
"AutoConfig": "chartinstruct_flant5_modeling.LlavaT5Config",
"AutoModelForSeq2SeqLM": "chartinstruct_flant5_modeling.LlavaT5ForConditionalGeneration"
},
"classifier_dropout": 0.0,
"d_ff": 5120,
"d_kv": 64,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"freeze_mm_mlp_adapter": false,
"image_aspect_ratio": "square",
"image_grid_pinpoints": null,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"mm_hidden_size": 1024,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -1,
"mm_vision_tower": "/home/masry20/projects/def-enamul/masry20/llms-models/unichart-encoder-512",
"model_type": "llava_t5",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 200,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": "summarize: "
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to German: "
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to French: "
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to Romanian: "
}
},
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"tune_mm_mlp_adapter": false,
"use_cache": false,
"use_mm_proj": true,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"DonutSwinModel"
],
"attention_probs_dropout_prob": 0.0,
"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,
"depths": [
2,
2,
14,
2
],
"diversity_penalty": 0.0,
"do_sample": false,
"drop_path_rate": 0.1,
"early_stopping": false,
"embed_dim": 128,
"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_dropout_prob": 0.0,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": [
512,
512
],
"initializer_range": 0.02,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"mlp_ratio": 4.0,
"model_type": "donut-swin",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_heads": [
4,
8,
16,
32
],
"num_layers": 4,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 4,
"path_norm": true,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"qkv_bias": true,
"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,
"torch_dtype": "float32",
"torchscript": false,
"typical_p": 1.0,
"use_absolute_embeddings": false,
"use_bfloat16": false,
"window_size": 10
},
"vocab_size": 32128
}