File size: 1,336 Bytes
f918df3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
{
"_name_or_path": "/home/models/llava-qwen-2-7b-OFA-Syschinese-clip-huge-mergeddata_lora_chinesedatasets_lora_0729_warmup0_1/",
"architectures": [
"LlavaForConditionalGeneration"
],
"ignore_index": -100,
"image_token_index": 151646,
"model_type": "llava",
"pad_token_id": 151643,
"projector_hidden_act": "gelu",
"text_config": {
"_name_or_path": "/home/models/Qwen2-7B-Instruct/",
"architectures": [
"Qwen2ForCausalLM"
],
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_size": 3584,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"torch_dtype": "bfloat16",
"use_sliding_window": false,
"vocab_size": 152064
},
"torch_dtype": "float16",
"transformers_version": "4.42.1",
"vision_config": {
"dropout": 0.0,
"hidden_size": 1280,
"image_size": 224,
"intermediate_size": 5120,
"model_type": "chinese_clip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 32,
"patch_size": 14,
"projection_dim": 1024
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "default"
}
|