cogvlm2-llama3-caption / config.json
Ubuntu
init
600a885
{
"architectures": [
"CogVLMVideoForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_cogvlm.CogVLMConfig",
"AutoModelForCausalLM": "modeling_cogvlm.CogVLMVideoForCausalLM"
},
"bos_token_id": 128000,
"eos_token_id": 128001,
"pad_token_id": 128002,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 2048,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_multi_query_heads": 8,
"rms_norm_eps": 1e-05,
"template_version": "base",
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.1",
"use_cache": true,
"vision_config": {
"dropout_prob": 0.0,
"hidden_act": "gelu",
"hidden_size": 1792,
"image_size": 224,
"in_channels": 3,
"intermediate_size": 15360,
"layer_norm_eps": 1e-06,
"num_heads": 16,
"num_hidden_layers": 63,
"num_positions": 257,
"patch_size": 14
},
"vocab_size": 128256
}