Visual Question Answering
Transformers
Safetensors
Chinese
English
QH_360VL
text-generation
custom_code
360VL-8B / proj_config.json
xiechunyu's picture
first commit
16f1801
{
"_commit_hash": null,
"_name_or_path": "",
"architectures": [
"HoneybeeForConditionalGeneration"
],
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 13824,
"keys_to_ignore_at_inference": [
"past_key_values"
],
"lm_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"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,
"delta_model_name_or_path": 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,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"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": "mllm_lm",
"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,
"pretrained_lm_name_or_path": "/hbox2dir/vicuna-13b-v1.5",
"pretrained_tokenizer_name_or_path": "/hbox2dir/vicuna-13b-v1.5",
"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,
"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": null,
"torchscript": false,
"transformers_version": "4.30.2",
"typical_p": 1.0,
"use_bfloat16": false
},
"max_position_embeddings": 4096,
"model_type": "mllm",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"num_query_tokens": 576,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"text_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": [
"LlamaForCausalLM"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 1,
"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": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 5120,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 13824,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 4096,
"max_position_embeddings": 4096,
"min_length": 0,
"model_type": "llama",
"no_repeat_ngram_size": 0,
"num_attention_heads": 40,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"prefix": null,
"pretraining_tp": 1,
"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": null,
"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": "float16",
"torchscript": false,
"transformers_version": "4.30.2",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 32000
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": null,
"use_cache": true,
"use_decoder_only_language_model": true,
"vision_config": {
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"attention_dropout": 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,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.0,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"encoder_type": "openai.clip",
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_size": 336,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"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,
"model_type": "clip_vision_model",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_channels": 3,
"num_hidden_layers": 24,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"pretrained_vision_name_or_path": "/hbox2dir/clip-vit-large-patch14-336",
"problem_type": null,
"projection_dim": 768,
"pruned_heads": {},
"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": null,
"torchscript": false,
"transformers_version": "4.30.2",
"typical_p": 1.0,
"use_bfloat16": false
},
"visual_projector_config": {
"_name_or_path": "",
"add_cross_attention": false,
"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,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"depth": 3,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_hidden_size": 1024,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"feature_layer_index": -2,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-06,
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"mlp_depth": 2,
"model_type": "mllm_visual_projector",
"no_repeat_ngram_size": 0,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_eos_tokens": 0,
"num_hidden_layers": 6,
"num_queries": 576,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"pos_emb": true,
"prefix": null,
"prenorm": false,
"problem_type": null,
"projector_type": "c-abs",
"pruned_heads": {},
"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": null,
"torchscript": false,
"transformers_version": "4.30.2",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cls": true
},
"vocab_size": 32000
}