|
{
|
|
"_name_or_path": "Idefics3-8B-Llama3",
|
|
"architectures": [
|
|
"Idefics3ForConditionalGeneration"
|
|
],
|
|
"image_token_id": 128257,
|
|
"model_type": "idefics3",
|
|
"quantization_config": {
|
|
"bnb_4bit_compute_dtype": "bfloat16",
|
|
"bnb_4bit_quant_storage": "uint8",
|
|
"bnb_4bit_quant_type": "nf4",
|
|
"bnb_4bit_use_double_quant": true,
|
|
"llm_int8_enable_fp32_cpu_offload": false,
|
|
"llm_int8_has_fp16_weight": false,
|
|
"llm_int8_skip_modules": null,
|
|
"llm_int8_threshold": 6.0,
|
|
"load_in_4bit": true,
|
|
"load_in_8bit": false
|
|
},
|
|
"scale_factor": 2,
|
|
"text_config": {
|
|
"_attn_implementation_autoset": false,
|
|
"_flash_attn_2_enabled": true,
|
|
"_name_or_path": "None",
|
|
"add_cross_attention": false,
|
|
"architectures": [
|
|
"Idefics3ForVisionText2Text"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_idefics3.Idefics3Config",
|
|
"AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
|
|
},
|
|
"bad_words_ids": null,
|
|
"begin_suppress_tokens": null,
|
|
"bos_token_id": 128000,
|
|
"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": [
|
|
128001,
|
|
128008,
|
|
128009
|
|
],
|
|
"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": 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,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"neftune_noise_alpha": 0.0,
|
|
"no_repeat_ngram_size": 0,
|
|
"num_attention_heads": 32,
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"num_return_sequences": 1,
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": 128002,
|
|
"perceiver_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": "silu",
|
|
"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": "idefics3",
|
|
"no_repeat_ngram_size": 0,
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_key_value_heads": 1,
|
|
"num_return_sequences": 1,
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": 128002,
|
|
"prefix": null,
|
|
"problem_type": null,
|
|
"pruned_heads": {},
|
|
"qk_layer_norms_perceiver": false,
|
|
"remove_invalid_values": false,
|
|
"repetition_penalty": 1.0,
|
|
"resampler_depth": 6,
|
|
"resampler_head_dim": 96,
|
|
"resampler_n_heads": 16,
|
|
"resampler_n_latents": 64,
|
|
"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": "4.43.2",
|
|
"typical_p": 1.0,
|
|
"use_bfloat16": false
|
|
},
|
|
"prefix": null,
|
|
"pretraining_tp": 1,
|
|
"problem_type": null,
|
|
"pruned_heads": {},
|
|
"qk_layer_norms": false,
|
|
"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,
|
|
"use_resampler": false,
|
|
"vocab_size": 128259
|
|
},
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.47.0.dev0",
|
|
"use_cache": true,
|
|
"vision_config": {
|
|
"_attn_implementation_autoset": false,
|
|
"_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": "gelu_pytorch_tanh",
|
|
"hidden_size": 1152,
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"image_size": 364,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 4304,
|
|
"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,
|
|
"model_type": "idefics3",
|
|
"no_repeat_ngram_size": 0,
|
|
"num_attention_heads": 16,
|
|
"num_beam_groups": 1,
|
|
"num_beams": 1,
|
|
"num_channels": 3,
|
|
"num_hidden_layers": 27,
|
|
"num_return_sequences": 1,
|
|
"old_vision_model_name": "/fsx/hugo/siglip-so400m-14-364-flash-attn2-navit",
|
|
"output_attentions": false,
|
|
"output_hidden_states": false,
|
|
"output_scores": false,
|
|
"pad_token_id": 128002,
|
|
"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,
|
|
"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
|
|
}
|
|
} |