|
{ |
|
"architectures": [ |
|
"LlavaNextForConditionalGeneration" |
|
], |
|
"image_grid_pinpoints": [ |
|
[ |
|
384, |
|
384 |
|
], |
|
[ |
|
384, |
|
768 |
|
], |
|
[ |
|
768, |
|
384 |
|
], |
|
[ |
|
384, |
|
1152 |
|
], |
|
[ |
|
1152, |
|
384 |
|
], |
|
[ |
|
384, |
|
1536 |
|
], |
|
[ |
|
768, |
|
768 |
|
], |
|
[ |
|
1536, |
|
384 |
|
], |
|
[ |
|
384, |
|
1920 |
|
], |
|
[ |
|
1920, |
|
384 |
|
], |
|
[ |
|
384, |
|
2304 |
|
], |
|
[ |
|
768, |
|
1152 |
|
], |
|
[ |
|
1152, |
|
768 |
|
], |
|
[ |
|
2304, |
|
384 |
|
] |
|
], |
|
"image_seq_length": 576, |
|
"image_token_index": 128000, |
|
"model_type": "llava_next", |
|
"multimodal_projector_bias": true, |
|
"projector_hidden_act": "gelu", |
|
"text_config": { |
|
"_name_or_path": "/mnt/scratch-artemis/miguelramos/LC-EuroLLM/HF_MODELS/EuroLLM-9B-Legacy-32k/", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 12288, |
|
"max_position_embeddings": 32768, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 42, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 1000000, |
|
"torch_dtype": "bfloat16", |
|
"use_cache": true, |
|
"vocab_size": 128001 |
|
}, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.52.0.dev0", |
|
"use_image_newline_parameter": true, |
|
"vision_config": { |
|
"attention_dropout": 0.0, |
|
"hidden_act": "gelu_pytorch_tanh", |
|
"hidden_size": 1152, |
|
"image_size": 384, |
|
"intermediate_size": 4304, |
|
"layer_norm_eps": 1e-06, |
|
"model_type": "siglip_vision_model", |
|
"num_attention_heads": 16, |
|
"num_channels": 3, |
|
"num_hidden_layers": 26, |
|
"patch_size": 14, |
|
"vision_use_head": false |
|
}, |
|
"vision_feature_layer": -1, |
|
"vision_feature_select_strategy": "full" |
|
} |
|
|