初始化项目,由ModelHub XC社区提供模型

Model: ManishThota/Ollama_Video_llama_7B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-21 10:41:54 +08:00
commit dc7f62fbac
20 changed files with 3012 additions and 0 deletions

62
vvl_vit/config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"_name_or_path": "vit-large336-custom",
"architectures": [
"CLIPVisionModel"
],
"attention_dropout": 0.0,
"dropout": 0.0,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"image_size": 336,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"image_aspect_ratio": "anyres",
"image_crop_resolution": 224,
"image_grid_pinpoints": [
[
336,
672
],
[
672,
336
],
[
672,
672
],
[
1008,
336
],
[
336,
1008
]
],
"image_split_resolution": 224,
"initializer_range": 0.02,
"max_length": 4096,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "spatial_unpad",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": null,
"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__": "openai/clip-vit-large-patch14-336",
"mm_vision_tower_lr": 2e-06
}

3
vvl_vit/llava.projector Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37370de2db3f3a501e1aecff9712df83894017956d4870825849b193be7f0ed1
size 83920640

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab553f9a6ecf2c73d9073f56b3b45fcc30442cabbd3795f8aec0c9c1a3a24d4d
size 624434720

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d99f87cc57e547eb3a0287b753ca6500aa4e1505c3ead22066f48360bfd485c6
size 607116558