Any-to-Any
Transformers
Safetensors
neo_chat
feature-extraction
multimodal
text-to-image
image-to-text
image-editing
interleaved-generation
custom_code
Instructions to use hardcoremoore/SenseNova-U1-8B-MoT-Infographic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hardcoremoore/SenseNova-U1-8B-MoT-Infographic with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hardcoremoore/SenseNova-U1-8B-MoT-Infographic", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "NEOChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_neo_chat.NEOChatConfig", | |
| "AutoModel": "modeling_neo_chat.NEOChatModel", | |
| "AutoModelForCausalLM": "modeling_neo_chat.NEOChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "eos_token_id": 151645, | |
| "llm_config": { | |
| "_name_or_path": null, | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 262144, | |
| "max_position_embeddings_hw": 10000, | |
| "max_window_layers": 42, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000.0, | |
| "rope_theta_hw": 10000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": false, | |
| "use_deepep": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936, | |
| "pure_llm": false | |
| }, | |
| "model_type": "neo_chat", | |
| "pad_token_id": 151643, | |
| "template": "neo1_0", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.2", | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "min_pixels": 65536, | |
| "max_pixels": 16777216, | |
| "patch_size": 16, | |
| "timestep_shift": 1.0, | |
| "time_schedule": "standard", | |
| "time_shift_type": "exponential", | |
| "base_shift": 0.5, | |
| "max_shift": 1.15, | |
| "base_image_seq_len": 64, | |
| "max_image_seq_len": 4096, | |
| "noise_scale_mode": "resolution", | |
| "noise_scale_base_image_seq_len": 64, | |
| "add_noise_scale_embedding": true, | |
| "noise_scale_max_value": 8.0, | |
| "noise_scale": 1.0, | |
| "P_mean": -0.8, | |
| "P_std": 0.8, | |
| "t_eps": 0.05, | |
| "fm_head_dim": 1536, | |
| "fm_head_layers": 2, | |
| "fm_head_mlp_ratio": 1, | |
| "extra_num_layers_post": 0, | |
| "concat_time_token_num": 0, | |
| "use_pixel_head": false, | |
| "use_adaLN": false, | |
| "vision_config": { | |
| "architectures": [ | |
| "NEOVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_neo_vit.NEOVisionConfig", | |
| "AutoModel": "modeling_neo_vit.NEOVisionModel" | |
| }, | |
| "llm_hidden_size": 4096, | |
| "downsample_ratio": 0.5, | |
| "hidden_size": 1024, | |
| "model_type": "neo_vision", | |
| "rope_theta_vision": 10000.0, | |
| "max_position_embeddings_vision": 10000, | |
| "num_channels": 3, | |
| "patch_size": 16, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.2", | |
| "min_pixels": 65536, | |
| "max_pixels": 16777216 | |
| } | |
| } |