Feature Extraction
Transformers
Safetensors
multilingual
neomme
multimodal
document-understanding
masked-language-modeling
long-context
Instructions to use Hcompany/NeoMME-800M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hcompany/NeoMME-800M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Hcompany/NeoMME-800M")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Hcompany/NeoMME-800M") model = AutoModel.from_pretrained("Hcompany/NeoMME-800M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 2,141 Bytes
336ba04 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | {
"architectures": [
"NeoMMEModel"
],
"attention_bias": false,
"attention_dropout": 0.0,
"document_token_id": 5,
"dtype": "bfloat16",
"embedding_dim": 128,
"embedding_rank": 256,
"head_dim": 64,
"hidden_act": "relu2",
"hidden_size": 1792,
"image_token_id": 6,
"initializer_range": 0.02,
"intermediate_size": 6400,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "neomme",
"norm_eps": 1e-06,
"num_attention_heads": 28,
"num_hidden_layers": 20,
"num_key_value_heads": 7,
"pad_token_id": 0,
"patch_size": 32,
"per_layer_config": {
"01": {
"sliding_window": 1024
},
"03": {
"sliding_window": 1024
},
"05": {
"sliding_window": null
},
"06": {
"sliding_window": 1024
},
"08": {
"sliding_window": 1024
},
"10": {
"sliding_window": 1024
},
"11": {
"sliding_window": null
},
"13": {
"sliding_window": 1024
},
"15": {
"sliding_window": 1024
},
"17": {
"sliding_window": null
},
"18": {
"sliding_window": 1024
},
"19": {
"sliding_window": null
}
},
"residual_multiplier": 0.15811388300841897,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.25,
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_attention": {
"partial_rotary_factor": 1.0,
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 256,
"tie_word_embeddings": true,
"transformers_version": "5.16.0.dev0",
"vocab_size": 131072
}
|