Text Generation
Transformers
Safetensors
English
llava
multimodal
conversational
Eval Results
Inference Endpoints
LLaVA-Video-72B-Qwen2 / config.json
ZhangYuanhan's picture
Upload config.json with huggingface_hub
725314e verified
raw
history blame
3.64 kB
{
"_name_or_path": "/mnt/bn/vl-research/checkpoints/onevision/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-72B-Instruct-final_to_ov_am9_july31v4/checkpoint-9000",
"add_faster_video": false,
"add_time_instruction": true,
"vocab_size": 152064,
"architectures": [
"LlavaQwenForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"faster_token_stride": 10,
"force_sample": true,
"hidden_act": "silu",
"hidden_size": 8192,
"ignore_index": -100,
"image_aspect_ratio": "anyres_max_9",
"image_crop_resolution": null,
"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_split_resolution": null,
"image_token_index": 151646,
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 32768,
"max_window_layers": 80,
"mm_hidden_size": 1152,
"mm_newline_position": "grid",
"mm_patch_merge_type": "spatial_unpad",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": null,
"mm_spatial_pool_mode": "bilinear",
"mm_spatial_pool_stride": 2,
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "google/siglip-so400m-patch14-384",
"mm_vision_tower_lr": 2e-06,
"model_type": "llava",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pos_skipping_range": 4096,
"projector_hidden_act": "gelu",
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"text_config": {
"model_type": "llama"
},
"tie_word_embeddings": false,
"tokenizer_model_max_length": 32768,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0.dev0",
"use_cache": true,
"use_mm_proj": true,
"use_pos_skipping": false,
"use_sliding_window": false,
"vision_config": {
"hidden_size": 1024,
"image_size": 336,
"intermediate_size": 4096,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"vocab_size": 32000
},
"vision_feature_layer": -2,
"vision_feature_select_strategy": "default",
"vision_tower_pretrained": null
}