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"
   ],
@@ -136,7 +136,8 @@
     "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-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b310fd907084c3846721f58067147e1c6a35670b1edcf2492bc794db83005f2d
-size 4984228696
+oid sha256:e3f2c2c9f817c2187e7fc3fc8e1f925ec4821e317a1097602bb0d0c88d76d874
+size 4970053136

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7b843a130374112910730baa71ff3784aa650e995a63c810c4395b0e93b744
+oid sha256:75850f91c5085aff924c8e090c475a003b941b7dded84d7bfb8bc10ea2b9379c
 size 1451273752

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16267092480
+    "total_size": 16252918272
   },
   "weight_map": {
     "connector.proj.weight": "model-00004-of-00004.safetensors",
@@ -457,17 +457,6 @@
     "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
     "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.attention.in_proj_bias": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.attention.in_proj_weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.attention.out_proj.bias": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.attention.out_proj.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.layernorm.bias": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.layernorm.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.mlp.fc1.bias": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.mlp.fc1.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.mlp.fc2.bias": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.mlp.fc2.weight": "model-00001-of-00004.safetensors",
-    "vision_tower.vision_model.head.probe": "model-00001-of-00004.safetensors",
     "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
     "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
   }