InternVL2_5-1B-4bit / config.json
prince-canuma's picture
Update config.json
6583ff1 verified
{
"_attn_implementation_internal": null,
"_commit_hash": "9d423ea1ae9f893897ee3f7493141073f5afcf22",
"_output_attentions": false,
"add_cross_attention": false,
"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,
"downsample_ratio": 0.5,
"dynamic_image_size": true,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"force_image_size": 448,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_token_index": 151667,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"text_config": {
"vocab_size": 151674,
"max_position_embeddings": 32768,
"hidden_size": 896,
"intermediate_size": 4864,
"num_hidden_layers": 24,
"num_attention_heads": 14,
"use_sliding_window": false,
"sliding_window": null,
"max_window_layers": 21,
"num_key_value_heads": 2,
"hidden_act": "silu",
"initializer_range": 0.02,
"rms_norm_eps": 1e-06,
"use_cache": true,
"rope_theta": 1000000.0,
"rope_scaling": null,
"attention_dropout": 0.0,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"torch_dtype": "bfloat16",
"pruned_heads": {},
"tie_word_embeddings": false,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": 151643,
"pad_token_id": null,
"eos_token_id": 151645,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
"transformers_version": "4.54.0",
"model_type": "qwen2",
"tf_legacy_loss": false,
"use_bfloat16": true,
"output_attentions": false
},
"max_dynamic_patch": 12,
"max_length": 20,
"min_dynamic_patch": 1,
"min_length": 0,
"model_type": "internvl_chat",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"ps_version": "v2",
"quantization": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"select_layer": -1,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"template": "internvl2_5",
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": false,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"transformers_version": null,
"typical_p": 1.0,
"use_backbone_lora": 0,
"use_bfloat16": false,
"use_llm_lora": 0,
"use_thumbnail": true,
"vision_config": {
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"torch_dtype": "bfloat16",
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"_name_or_path": "",
"transformers_version": "4.54.0",
"model_type": "intern_vit_6b",
"use_bfloat16": true,
"tf_legacy_loss": false,
"hidden_size": 1024,
"intermediate_size": 4096,
"dropout": 0.0,
"drop_path_rate": 0.0,
"num_hidden_layers": 24,
"num_attention_heads": 16,
"num_channels": 3,
"patch_size": 14,
"image_size": 448,
"initializer_range": 0.02,
"initializer_factor": 1.0,
"attention_dropout": 0.0,
"layer_norm_eps": 1e-06,
"hidden_act": "gelu",
"norm_type": "layer_norm",
"qkv_bias": true,
"qk_normalization": false,
"use_flash_attn": true,
"output_attentions": false
}
}