swapnil7777's picture
Upload LlavaForConditionalGeneration
b5c258a verified
raw
history blame
15.7 kB
{
"_name_or_path": "/root/.cache/huggingface/hub/models--Aranya31--llava_epoch4_dermnet/snapshots/13afb4a577b14e2386a6f99a09d380ce3167dfec",
"architectures": [
"LlavaForConditionalGeneration"
],
"ignore_index": -100,
"image_seq_length": 576,
"image_token_index": 32000,
"model_type": "llava",
"pad_token_id": 32001,
"projector_hidden_act": "gelu",
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": "memoryless",
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"global_compression_ratio": 1.1620658104955142,
"ignore": [
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.0.mlp.fc1",
"vision_tower.vision_model.encoder.layers.0.mlp.fc2",
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.1.mlp.fc1",
"vision_tower.vision_model.encoder.layers.1.mlp.fc2",
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.2.mlp.fc1",
"vision_tower.vision_model.encoder.layers.2.mlp.fc2",
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.3.mlp.fc1",
"vision_tower.vision_model.encoder.layers.3.mlp.fc2",
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.4.mlp.fc1",
"vision_tower.vision_model.encoder.layers.4.mlp.fc2",
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.5.mlp.fc1",
"vision_tower.vision_model.encoder.layers.5.mlp.fc2",
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.6.mlp.fc1",
"vision_tower.vision_model.encoder.layers.6.mlp.fc2",
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.7.mlp.fc1",
"vision_tower.vision_model.encoder.layers.7.mlp.fc2",
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.8.mlp.fc1",
"vision_tower.vision_model.encoder.layers.8.mlp.fc2",
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.9.mlp.fc1",
"vision_tower.vision_model.encoder.layers.9.mlp.fc2",
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.10.mlp.fc1",
"vision_tower.vision_model.encoder.layers.10.mlp.fc2",
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.11.mlp.fc1",
"vision_tower.vision_model.encoder.layers.11.mlp.fc2",
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.12.mlp.fc1",
"vision_tower.vision_model.encoder.layers.12.mlp.fc2",
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.13.mlp.fc1",
"vision_tower.vision_model.encoder.layers.13.mlp.fc2",
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.14.mlp.fc1",
"vision_tower.vision_model.encoder.layers.14.mlp.fc2",
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.15.mlp.fc1",
"vision_tower.vision_model.encoder.layers.15.mlp.fc2",
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.16.mlp.fc1",
"vision_tower.vision_model.encoder.layers.16.mlp.fc2",
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.17.mlp.fc1",
"vision_tower.vision_model.encoder.layers.17.mlp.fc2",
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.18.mlp.fc1",
"vision_tower.vision_model.encoder.layers.18.mlp.fc2",
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.19.mlp.fc1",
"vision_tower.vision_model.encoder.layers.19.mlp.fc2",
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.20.mlp.fc1",
"vision_tower.vision_model.encoder.layers.20.mlp.fc2",
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.21.mlp.fc1",
"vision_tower.vision_model.encoder.layers.21.mlp.fc2",
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.22.mlp.fc1",
"vision_tower.vision_model.encoder.layers.22.mlp.fc2",
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
"vision_tower.vision_model.encoder.layers.23.mlp.fc1",
"vision_tower.vision_model.encoder.layers.23.mlp.fc2",
"multi_modal_projector.linear_1",
"multi_modal_projector.linear_2",
"language_model.lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed"
},
"text_config": {
"_name_or_path": "lmsys/vicuna-7b-v1.5",
"add_cross_attention": false,
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"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,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 11008,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 4096,
"min_length": 0,
"mlp_bias": false,
"model_type": "llama",
"no_repeat_ngram_size": 0,
"num_attention_heads": 32,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"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,
"rope_theta": 10000.0,
"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": "float16",
"torchscript": false,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 32064
},
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.45.1",
"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,
"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": "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,
"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,
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 32000
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "default",
"vocab_size": 32064
}