|
{ |
|
"_name_or_path": "/root/.cache/huggingface/hub/models--allenai--Molmo-7B-D-0924/snapshots/1721478b71306fb7dc671176d5c204dc7a4d27d7", |
|
"architectures": [ |
|
"MolmoForCausalLM" |
|
], |
|
"attention_layer_norm": false, |
|
"auto_map": { |
|
"AutoConfig": "config_molmo.MolmoConfig", |
|
"AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM" |
|
}, |
|
"clip_qkv": null, |
|
"embedding_size": 152064, |
|
"hidden_size": 3584, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 37888, |
|
"layer_norm_eps": 1e-06, |
|
"layer_norm_type": "rms", |
|
"max_position_embeddings": 4096, |
|
"model_type": "molmo", |
|
"norm_after": false, |
|
"num_attention_heads": 28, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 4, |
|
"qkv_bias": true, |
|
"quantization_config": { |
|
"config_groups": { |
|
"group_0": { |
|
"input_activations": { |
|
"actorder": null, |
|
"block_structure": null, |
|
"dynamic": true, |
|
"group_size": null, |
|
"num_bits": 8, |
|
"observer": null, |
|
"observer_kwargs": {}, |
|
"strategy": "token", |
|
"symmetric": true, |
|
"type": "float" |
|
}, |
|
"output_activations": null, |
|
"targets": [ |
|
"Linear" |
|
], |
|
"weights": { |
|
"actorder": null, |
|
"block_structure": null, |
|
"dynamic": false, |
|
"group_size": null, |
|
"num_bits": 8, |
|
"observer": "minmax", |
|
"observer_kwargs": {}, |
|
"strategy": "channel", |
|
"symmetric": true, |
|
"type": "float" |
|
} |
|
} |
|
}, |
|
"format": "float-quantized", |
|
"global_compression_ratio": 1.2045747559103401, |
|
"ignore": [ |
|
"model.vision_backbone.image_vit.patch_embedding", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.0.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.1.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.2.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.3.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.4.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.5.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.6.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.7.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.8.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.9.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.10.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.11.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.12.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.13.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.14.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.15.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.16.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.17.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.18.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.19.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.20.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.21.feed_forward.w2", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.attention.wq", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.attention.wk", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.attention.wv", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.attention.wo", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w1", |
|
"model.vision_backbone.image_vit.transformer.resblocks.22.feed_forward.w2", |
|
"model.vision_backbone.image_pooling_2d.wq", |
|
"model.vision_backbone.image_pooling_2d.wk", |
|
"model.vision_backbone.image_pooling_2d.wv", |
|
"model.vision_backbone.image_pooling_2d.wo", |
|
"model.vision_backbone.image_projector.w1", |
|
"model.vision_backbone.image_projector.w2", |
|
"model.vision_backbone.image_projector.w3" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "compressed" |
|
}, |
|
"rope_theta": 1000000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.46.1", |
|
"use_cache": true, |
|
"use_position_ids": true, |
|
"vocab_size": 152064, |
|
"weight_tying": false |
|
} |