Upload folder using huggingface_hub

.gitattributes

@@ -39,3 +39,6 @@ LLaVA-NeXT-Video-7B-DPO-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 llava.clip filter=lfs diff=lfs merge=lfs -text
 llava.projector filter=lfs diff=lfs merge=lfs -text
 vit/mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-model-f32.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-model-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,16 +1,25 @@
 {
-  "_name_or_path": "model_zoo/LLM/vicuna/7B-V1.5",
+  "_name_or_path": "vit-large336-custom",
   "architectures": [
-    "LlavaLlamaForCausalLM"
+    "CLIPVisionModel"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "freeze_mm_mlp_adapter": true,
-  "freeze_mm_vision_resampler": false,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
+  "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": [
@@ -37,41 +46,17 @@
   ],
   "image_split_resolution": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
+  "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": "spatial_pool",
-  "mm_spatial_pool_mode": "average",
-  "mm_spatial_pool_out_channels": 1024,
-  "mm_spatial_pool_stride": 2,
+  "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": null,
-  "model_type": "llava",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 32,
-  "pad_token_id": 0,
-  "patchify_video_feature": false,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 4096,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.2",
-  "tune_mm_mlp_adapter": false,
-  "tune_mm_vision_resampler": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": true,
-  "use_mm_proj": true,
-  "vocab_size": 32000
+  "mm_vision_tower__": "openai/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06
 }

mmproj-model-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f870142318cb91f83448d7c8382b6f9136e160cfeca0ddce252d1e7a63deb357
+size 624451168

mmproj-model-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1477e04fed50d26a03dc7faf8847a4db9ce9296285f2b8a90f37f55cb134f6
+size 1204446816

mmproj-model-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7b67aa135e0a95a85c8765a59b035b425478bae0c1d7a6a2e6a9c5e073ad20
+size 1204446816

pytorch_model.bin

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