| { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_helium1_casa.Helium1CASAConfig", | |
| "AutoModel": "modeling_helium1_casa.V2Helium1" | |
| }, | |
| "bos_token_id": 1, | |
| "casa_attention": false, | |
| "casa_delta_w": true, | |
| "casa_use_asymetric_qkv": true, | |
| "casa_windows": "images", | |
| "eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "mask_squash_blockwise": false, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "Helium1_VL_2B", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 3, | |
| "post_image_tokens": [], | |
| "pre_image_tokens": [], | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-08, | |
| "rope_scaling": null, | |
| "rope_theta": 20000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "vision_config": { | |
| "depth": 32, | |
| "fullatt_block_indexes": [ | |
| 7, | |
| 15, | |
| 23, | |
| 31 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "image_mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "image_std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "intermediate_size": 3420, | |
| "model_type": "qwen2_5_vl", | |
| "num_heads": 16, | |
| "out_dim": 2048, | |
| "out_hidden_size": 2048, | |
| "patch_size": 14, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 14, | |
| "temporal_patch_size": 1, | |
| "tokens_per_second": 2, | |
| "window_size": 112 | |
| }, | |
| "vocab_size": 64000, | |
| "xa_custom_norm": false, | |
| "xa_layers": [], | |
| "xa_norm_on_images": false, | |
| "xa_order": "ca_first", | |
| "xa_update_image_embeds": false | |
| } |