hf-transformers-bot's picture
Update tiny models for Mistral3ForConditionalGeneration
1eb451b verified
Raw
History Blame Contribute Delete
1.5 kB
{
"architectures": [
"Mistral3ForConditionalGeneration"
],
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"image_seq_length": 4,
"image_token_index": 1,
"model_type": "mistral3",
"multimodal_projector_bias": false,
"pad_token_id": 11,
"projector_hidden_act": "gelu",
"spatial_merge_size": 2,
"text_config": {
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 8,
"hidden_act": "silu",
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 37,
"max_position_embeddings": 512,
"model_type": "mistral",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"pad_token_id": 11,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 1000000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 131072
},
"tie_word_embeddings": true,
"transformers_version": "5.16.0.dev0",
"vision_config": {
"attention_dropout": 0.0,
"head_dim": 8,
"hidden_act": "gelu",
"hidden_size": 32,
"image_size": 30,
"initializer_range": 0.02,
"intermediate_size": 37,
"model_type": "pixtral",
"num_attention_heads": 4,
"num_channels": 3,
"num_hidden_layers": 2,
"patch_size": 6,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"vision_feature_layer": -1
}