{ "_commit_hash": "32d8bf4936ad1b3943c839143d9783a081c2e6f6", "_name_or_path": "/mnt/scratch/huggingface/hub/models--nvidia--NVLM-D-72B/snapshots/32d8bf4936ad1b3943c839143d9783a081c2e6f6", "architectures": [ "NVLM_D_Model" ], "auto_map": { "AutoConfig": "configuration_nvlm_d.NVLM_D_Config", "AutoModel": "modeling_nvlm_d.NVLM_D_Model", "AutoModelForCausalLM": "modeling_nvlm_d.NVLM_D_Model" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2-72B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_bias": true, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "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": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 8192, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 29568, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 28, "min_length": 0, "mlp_bias": false, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 64, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 80, "num_key_value_heads": 8, "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-06, "rope_scaling": { "factor": 3.0, "rope_type": "dynamic", "type": "dynamic" }, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 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": 1, "top_p": 0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.46.0.dev0", "typical_p": 1.0, "use_bfloat16": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "NVLM_D", "ps_version": "v2", "quantization_config": { "config_groups": { "group_0": { "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": 1.3978470298884915, "ignore": [ "vision_model.encoder.layers.0.attn.qkv", "vision_model.encoder.layers.0.attn.proj", "vision_model.encoder.layers.0.mlp.fc1", "vision_model.encoder.layers.0.mlp.fc2", "vision_model.encoder.layers.1.attn.qkv", "vision_model.encoder.layers.1.attn.proj", "vision_model.encoder.layers.1.mlp.fc1", "vision_model.encoder.layers.1.mlp.fc2", "vision_model.encoder.layers.2.attn.qkv", "vision_model.encoder.layers.2.attn.proj", "vision_model.encoder.layers.2.mlp.fc1", "vision_model.encoder.layers.2.mlp.fc2", "vision_model.encoder.layers.3.attn.qkv", "vision_model.encoder.layers.3.attn.proj", "vision_model.encoder.layers.3.mlp.fc1", "vision_model.encoder.layers.3.mlp.fc2", "vision_model.encoder.layers.4.attn.qkv", "vision_model.encoder.layers.4.attn.proj", "vision_model.encoder.layers.4.mlp.fc1", "vision_model.encoder.layers.4.mlp.fc2", "vision_model.encoder.layers.5.attn.qkv", "vision_model.encoder.layers.5.attn.proj", "vision_model.encoder.layers.5.mlp.fc1", "vision_model.encoder.layers.5.mlp.fc2", "vision_model.encoder.layers.6.attn.qkv", "vision_model.encoder.layers.6.attn.proj", "vision_model.encoder.layers.6.mlp.fc1", "vision_model.encoder.layers.6.mlp.fc2", "vision_model.encoder.layers.7.attn.qkv", "vision_model.encoder.layers.7.attn.proj", "vision_model.encoder.layers.7.mlp.fc1", "vision_model.encoder.layers.7.mlp.fc2", "vision_model.encoder.layers.8.attn.qkv", "vision_model.encoder.layers.8.attn.proj", "vision_model.encoder.layers.8.mlp.fc1", "vision_model.encoder.layers.8.mlp.fc2", "vision_model.encoder.layers.9.attn.qkv", "vision_model.encoder.layers.9.attn.proj", "vision_model.encoder.layers.9.mlp.fc1", "vision_model.encoder.layers.9.mlp.fc2", "vision_model.encoder.layers.10.attn.qkv", "vision_model.encoder.layers.10.attn.proj", "vision_model.encoder.layers.10.mlp.fc1", "vision_model.encoder.layers.10.mlp.fc2", "vision_model.encoder.layers.11.attn.qkv", "vision_model.encoder.layers.11.attn.proj", "vision_model.encoder.layers.11.mlp.fc1", "vision_model.encoder.layers.11.mlp.fc2", "vision_model.encoder.layers.12.attn.qkv", "vision_model.encoder.layers.12.attn.proj", "vision_model.encoder.layers.12.mlp.fc1", "vision_model.encoder.layers.12.mlp.fc2", "vision_model.encoder.layers.13.attn.qkv", "vision_model.encoder.layers.13.attn.proj", "vision_model.encoder.layers.13.mlp.fc1", "vision_model.encoder.layers.13.mlp.fc2", "vision_model.encoder.layers.14.attn.qkv", "vision_model.encoder.layers.14.attn.proj", "vision_model.encoder.layers.14.mlp.fc1", "vision_model.encoder.layers.14.mlp.fc2", "vision_model.encoder.layers.15.attn.qkv", "vision_model.encoder.layers.15.attn.proj", "vision_model.encoder.layers.15.mlp.fc1", "vision_model.encoder.layers.15.mlp.fc2", "vision_model.encoder.layers.16.attn.qkv", "vision_model.encoder.layers.16.attn.proj", "vision_model.encoder.layers.16.mlp.fc1", "vision_model.encoder.layers.16.mlp.fc2", "vision_model.encoder.layers.17.attn.qkv", "vision_model.encoder.layers.17.attn.proj", "vision_model.encoder.layers.17.mlp.fc1", "vision_model.encoder.layers.17.mlp.fc2", "vision_model.encoder.layers.18.attn.qkv", "vision_model.encoder.layers.18.attn.proj", "vision_model.encoder.layers.18.mlp.fc1", "vision_model.encoder.layers.18.mlp.fc2", "vision_model.encoder.layers.19.attn.qkv", "vision_model.encoder.layers.19.attn.proj", "vision_model.encoder.layers.19.mlp.fc1", "vision_model.encoder.layers.19.mlp.fc2", "vision_model.encoder.layers.20.attn.qkv", "vision_model.encoder.layers.20.attn.proj", "vision_model.encoder.layers.20.mlp.fc1", "vision_model.encoder.layers.20.mlp.fc2", "vision_model.encoder.layers.21.attn.qkv", "vision_model.encoder.layers.21.attn.proj", "vision_model.encoder.layers.21.mlp.fc1", "vision_model.encoder.layers.21.mlp.fc2", "vision_model.encoder.layers.22.attn.qkv", "vision_model.encoder.layers.22.attn.proj", "vision_model.encoder.layers.22.mlp.fc1", "vision_model.encoder.layers.22.mlp.fc2", "vision_model.encoder.layers.23.attn.qkv", "vision_model.encoder.layers.23.attn.proj", "vision_model.encoder.layers.23.mlp.fc1", "vision_model.encoder.layers.23.mlp.fc2", "vision_model.encoder.layers.24.attn.qkv", "vision_model.encoder.layers.24.attn.proj", "vision_model.encoder.layers.24.mlp.fc1", "vision_model.encoder.layers.24.mlp.fc2", "vision_model.encoder.layers.25.attn.qkv", "vision_model.encoder.layers.25.attn.proj", "vision_model.encoder.layers.25.mlp.fc1", "vision_model.encoder.layers.25.mlp.fc2", "vision_model.encoder.layers.26.attn.qkv", "vision_model.encoder.layers.26.attn.proj", "vision_model.encoder.layers.26.mlp.fc1", "vision_model.encoder.layers.26.mlp.fc2", "vision_model.encoder.layers.27.attn.qkv", "vision_model.encoder.layers.27.attn.proj", "vision_model.encoder.layers.27.mlp.fc1", "vision_model.encoder.layers.27.mlp.fc2", "vision_model.encoder.layers.28.attn.qkv", "vision_model.encoder.layers.28.attn.proj", "vision_model.encoder.layers.28.mlp.fc1", "vision_model.encoder.layers.28.mlp.fc2", "vision_model.encoder.layers.29.attn.qkv", "vision_model.encoder.layers.29.attn.proj", "vision_model.encoder.layers.29.mlp.fc1", "vision_model.encoder.layers.29.mlp.fc2", "vision_model.encoder.layers.30.attn.qkv", "vision_model.encoder.layers.30.attn.proj", "vision_model.encoder.layers.30.mlp.fc1", "vision_model.encoder.layers.30.mlp.fc2", "vision_model.encoder.layers.31.attn.qkv", "vision_model.encoder.layers.31.attn.proj", "vision_model.encoder.layers.31.mlp.fc1", "vision_model.encoder.layers.31.mlp.fc2", "vision_model.encoder.layers.32.attn.qkv", "vision_model.encoder.layers.32.attn.proj", "vision_model.encoder.layers.32.mlp.fc1", "vision_model.encoder.layers.32.mlp.fc2", "vision_model.encoder.layers.33.attn.qkv", "vision_model.encoder.layers.33.attn.proj", "vision_model.encoder.layers.33.mlp.fc1", "vision_model.encoder.layers.33.mlp.fc2", "vision_model.encoder.layers.34.attn.qkv", "vision_model.encoder.layers.34.attn.proj", "vision_model.encoder.layers.34.mlp.fc1", "vision_model.encoder.layers.34.mlp.fc2", "vision_model.encoder.layers.35.attn.qkv", "vision_model.encoder.layers.35.attn.proj", "vision_model.encoder.layers.35.mlp.fc1", "vision_model.encoder.layers.35.mlp.fc2", "vision_model.encoder.layers.36.attn.qkv", "vision_model.encoder.layers.36.attn.proj", "vision_model.encoder.layers.36.mlp.fc1", "vision_model.encoder.layers.36.mlp.fc2", "vision_model.encoder.layers.37.attn.qkv", "vision_model.encoder.layers.37.attn.proj", "vision_model.encoder.layers.37.mlp.fc1", "vision_model.encoder.layers.37.mlp.fc2", "vision_model.encoder.layers.38.attn.qkv", "vision_model.encoder.layers.38.attn.proj", "vision_model.encoder.layers.38.mlp.fc1", "vision_model.encoder.layers.38.mlp.fc2", "vision_model.encoder.layers.39.attn.qkv", "vision_model.encoder.layers.39.attn.proj", "vision_model.encoder.layers.39.mlp.fc1", "vision_model.encoder.layers.39.mlp.fc2", "vision_model.encoder.layers.40.attn.qkv", "vision_model.encoder.layers.40.attn.proj", "vision_model.encoder.layers.40.mlp.fc1", "vision_model.encoder.layers.40.mlp.fc2", "vision_model.encoder.layers.41.attn.qkv", "vision_model.encoder.layers.41.attn.proj", "vision_model.encoder.layers.41.mlp.fc1", "vision_model.encoder.layers.41.mlp.fc2", "vision_model.encoder.layers.42.attn.qkv", "vision_model.encoder.layers.42.attn.proj", "vision_model.encoder.layers.42.mlp.fc1", "vision_model.encoder.layers.42.mlp.fc2", "vision_model.encoder.layers.43.attn.qkv", "vision_model.encoder.layers.43.attn.proj", "vision_model.encoder.layers.43.mlp.fc1", "vision_model.encoder.layers.43.mlp.fc2", "vision_model.encoder.layers.44.attn.qkv", "vision_model.encoder.layers.44.attn.proj", "vision_model.encoder.layers.44.mlp.fc1", "vision_model.encoder.layers.44.mlp.fc2", "language_model.lm_head", "mlp1.1", "mlp1.3" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "select_layer": -1, "template": "chatml", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "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, "drop_path_rate": 0.0, "dropout": 0.0, "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", "hidden_size": 3200, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 0.1, "initializer_range": 1e-10, "intermediate_size": 12800, "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": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "rms_norm", "num_attention_heads": 25, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 45, "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, "pruned_heads": {}, "qk_normalization": true, "qkv_bias": false, "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": "bfloat16", "torchscript": false, "transformers_version": "4.46.0.dev0", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } }