Upload KawnIdefics3ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "kawn_idefics3_siglib14_384",
+  "_name_or_path": "kawn_cohere_8b_idefics3_siglib14_384",
   "architectures": [
     "KawnIdefics3ForConditionalGeneration"
   ],
@@ -149,7 +149,8 @@
     "model_type": "siglip_vision_model",
     "num_attention_heads": 12,
     "num_hidden_layers": 12,
-    "patch_size": 16
+    "patch_size": 16,
+    "vision_use_head": false
   },
   "vision_feature_layer": null
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f86ec0ba38169330c4fca398234f0bbce61dee6f7ff37b36754d84dfe5199c7
-size 4975717760
+oid sha256:c65d65bcfad0567f7c7f17f9cba815c427590d13544a976c80585ae9238afe8b
+size 4961542200

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278b2c01aee8c8b3f2c4826444c6e86518be01e196c5aa20da225424134c03d7
+oid sha256:4c379acc8596e90992a5fcf25c0c8cfe46c64fc29889f6edda2cc3682f23ed98
 size 453048752

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5428700160
+    "total_size": 5414525952
   },
   "weight_map": {
     "connector.proj.weight": "model-00002-of-00002.safetensors",
@@ -487,17 +487,6 @@
     "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.vision_model.head.probe": "model-00001-of-00002.safetensors",
     "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
     "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
   }