CoolFace
Modelpublic

nvidia/Eagle2-2B

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face
34likes3.3kdownloads
config.json127 linesDownload Raw Back to root
1{2    "_attn_implementation": "flash_attention_2",3    "_attn_implementation_autoset": false,4    "_name_or_path": "",5    "architectures": [6        "Eagle2_5_VLForConditionalGeneration"7    ],8    "auto_map": {9        "AutoConfig": "configuration_eagle2_5_vl.Eagle2_5_VLConfig",10        "AutoModel": "modeling_eagle2_5_vl.Eagle2_5_VLForConditionalGeneration"11      },12    "downsample_ratio": 0.5,13    "dynamic_image_size": true,14    "force_image_size": 448,15    "image_token_index": 151667,16    "max_dynamic_tiles": 12,17    "min_dynamic_tiles": 1,18    "mlp_checkpoint": false,19    "model_type": "eagle_2_5_vl",20    "pad2square": false,21    "pre_feature_reduction": false,22    "select_layer": -1,23    "template": "qwen2-chat",24    "text_config": {25        "_name_or_path": "./pretrained/Qwen2_5-1_5B-Instruct",26        "add_cross_attention": false,27        "architectures": [28            "Qwen2ForCausalLM"29        ],30        "attention_dropout": 0.0,31        "bad_words_ids": null,32        "begin_suppress_tokens": null,33        "bos_token_id": 151643,34        "chunk_size_feed_forward": 0,35        "cross_attention_hidden_size": null,36        "decoder_start_token_id": null,37        "diversity_penalty": 0.0,38        "do_sample": false,39        "early_stopping": false,40        "encoder_no_repeat_ngram_size": 0,41        "eos_token_id": 151645,42        "exponential_decay_length_penalty": null,43        "finetuning_task": null,44        "forced_bos_token_id": null,45        "forced_eos_token_id": null,46        "hidden_act": "silu",47        "hidden_size": 1536,48        "id2label": {49            "0": "LABEL_0",50            "1": "LABEL_1"51        },52        "initializer_range": 0.02,53        "intermediate_size": 8960,54        "is_decoder": false,55        "is_encoder_decoder": false,56        "label2id": {57            "LABEL_0": 0,58            "LABEL_1": 159        },60        "length_penalty": 1.0,61        "max_length": 20,62        "max_position_embeddings": 32768,63        "max_window_layers": 21,64        "min_length": 0,65        "model_type": "qwen2",66        "no_repeat_ngram_size": 0,67        "num_attention_heads": 12,68        "num_beam_groups": 1,69        "num_beams": 1,70        "num_hidden_layers": 28,71        "num_key_value_heads": 2,72        "num_return_sequences": 1,73        "output_attentions": false,74        "output_hidden_states": false,75        "output_scores": false,76        "pad_token_id": null,77        "prefix": null,78        "problem_type": null,79        "pruned_heads": {},80        "remove_invalid_values": false,81        "repetition_penalty": 1.0,82        "return_dict": true,83        "return_dict_in_generate": false,84        "rms_norm_eps": 1e-06,85        "rope_theta": 1000000.0,86        "sep_token_id": null,87        "sliding_window": 32768,88        "suppress_tokens": null,89        "task_specific_params": null,90        "temperature": 1.0,91        "tf_legacy_loss": false,92        "tie_encoder_decoder": false,93        "tie_word_embeddings": true,94        "tokenizer_class": null,95        "top_k": 50,96        "top_p": 1.0,97        "torch_dtype": "bfloat16",98        "torchscript": false,99        "transformers_version": "4.37.2",100        "typical_p": 1.0,101        "use_bfloat16": false,102        "use_cache": false,103        "use_sliding_window": false,104        "vocab_size": 151674105    },106    "tie_word_embeddings": true,107    "torch_dtype": "bfloat16",108    "transformers_version": "4.51.0",109    "use_backbone_lora": 0,110    "use_llm_lora": 0,111    "use_thumbnail": true,112    "vision_config": {113        "attention_dropout": 0.0,114        "drop_path_rate": 0.1,115        "hidden_act": "gelu_pytorch_tanh",116        "hidden_size": 1152,117        "image_size": 448,118        "intermediate_size": 4304,119        "layer_norm_eps": 1e-06,120        "model_type": "siglip_vision_model",121        "num_attention_heads": 16,122        "num_channels": 3,123        "num_hidden_layers": 27,124        "patch_size": 14,125        "torch_dtype": "bfloat16"126      }127}