litianjian's picture
add "mm_spatial_pool_mode" to config.
8521f25 verified
raw
history blame
2.57 kB
{
"_name_or_path": "/raid/raushan/si-7b",
"architectures": [
"LlavaOnevisionForConditionalGeneration"
],
"ignore_index": -100,
"image_grid_pinpoints": [
[
384,
384
],
[
384,
768
],
[
384,
1152
],
[
384,
1536
],
[
384,
1920
],
[
384,
2304
],
[
768,
384
],
[
768,
768
],
[
768,
1152
],
[
768,
1536
],
[
768,
1920
],
[
768,
2304
],
[
1152,
384
],
[
1152,
768
],
[
1152,
1152
],
[
1152,
1536
],
[
1152,
1920
],
[
1152,
2304
],
[
1536,
384
],
[
1536,
768
],
[
1536,
1152
],
[
1536,
1536
],
[
1536,
1920
],
[
1536,
2304
],
[
1920,
384
],
[
1920,
768
],
[
1920,
1152
],
[
1920,
1536
],
[
1920,
1920
],
[
1920,
2304
],
[
2304,
384
],
[
2304,
768
],
[
2304,
1152
],
[
2304,
1536
],
[
2304,
1920
],
[
2304,
2304
]
],
"image_token_index": 151646,
"model_type": "llava_onevision",
"projector_hidden_act": "gelu",
"mm_spatial_pool_mode": "bilinear",
"text_config": {
"_name_or_path": "Qwen/Qwen2-7B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_size": 3584,
"intermediate_size": 18944,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rope_theta": 1000000.0,
"torch_dtype": "bfloat16",
"vocab_size": 152128
},
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.45.0.dev0",
"use_image_newline_parameter": true,
"video_token_index": 151647,
"vision_aspect_ratio": "anyres_max_9",
"vision_config": {
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 26,
"patch_size": 14,
"vision_use_head": false
},
"vision_feature_layer": -1,
"vision_feature_select_strategy": "full"
}