Image-Text-to-Text
Transformers
PyTorch
English
doubutsu
conversational
custom_code
Inference Endpoints
doubutsu-2b-pt-378 / config.json
qtnx's picture
Upload folder using huggingface_hub
4b953b6 verified
raw
history blame
991 Bytes
{
"auto_map": {
"AutoConfig": "configuration_doubutsu.DoubutsuConfig",
"AutoModelForCausalLM": "modeling_doubutsu.Doubutsu"
},
"model_type": "doubutsu",
"text_config": {
"_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_size": 1536,
"intermediate_size": 8960,
"max_length": 32768,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16"
},
"transformers_version": "4.40.1",
"vision_config": {
"_name_or_path": "google/siglip-so400m-patch14-384",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
}
}