Add files using upload-large-folder tool

config.json

@@ -25,68 +25,66 @@
       "multi_modal_projector",
       "merger",
       "modality_projection",
-      "lm_head",
-      "multi_modal_projector",
-      "merger",
-      "modality_projection",
-      "vision_tower.vision_model.encoder.layers.23.self_attn",
+      "language_model.model.layers.0.self_attn",
       "language_model.model.layers.5.mlp",
+      "language_model.model.layers.2.mlp",
+      "language_model.model.layers.4.self_attn",
+      "vision_tower.vision_model.encoder.layers.24.self_attn",
       "vision_tower.vision_model.encoder.layers.26.self_attn",
-      "language_model.model.layers.4.mlp",
-      "language_model.model.layers.3.mlp",
-      "vision_tower.vision_model.encoder.layers.18.self_attn",
+      "vision_tower.vision_model.encoder.layers.23.self_attn",
+      "vision_tower.vision_model.encoder.layers.20.self_attn",
+      "vision_tower.vision_model.encoder.layers.25.self_attn",
       "vision_tower.vision_model.encoder.layers.19.self_attn",
       "vision_tower.vision_model.encoder.layers.21.self_attn",
-      "language_model.model.layers.1.mlp",
-      "vision_tower.vision_model.encoder.layers.17.mlp",
-      "vision_tower.vision_model.encoder.layers.24.self_attn",
-      "vision_tower.vision_model.encoder.layers.21.mlp",
-      "vision_tower.vision_model.encoder.layers.19.mlp",
-      "vision_tower.vision_model.encoder.layers.24.mlp",
-      "vision_tower.vision_model.encoder.layers.20.self_attn",
-      "vision_tower.vision_model.encoder.layers.22.self_attn",
-      "vision_tower.vision_model.encoder.layers.20.mlp",
       "vision_tower.vision_model.encoder.layers.25.mlp",
-      "language_model.model.layers.2.self_attn",
+      "vision_tower.vision_model.encoder.layers.22.self_attn",
+      "language_model.model.layers.3.mlp",
       "vision_tower.vision_model.encoder.layers.17.self_attn",
-      "language_model.model.layers.0.mlp",
-      "vision_tower.vision_model.encoder.layers.16.mlp",
       "vision_tower.vision_model.encoder.layers.23.mlp",
-      "vision_tower.vision_model.encoder.layers.22.mlp",
-      "vision_tower.vision_model.encoder.layers.13.mlp",
       "vision_tower.vision_model.encoder.layers.15.mlp",
+      "vision_tower.vision_model.encoder.layers.22.mlp",
       "vision_tower.vision_model.encoder.layers.18.mlp",
+      "vision_tower.vision_model.encoder.layers.18.self_attn",
+      "vision_tower.vision_model.encoder.layers.21.mlp",
+      "vision_tower.vision_model.encoder.layers.17.mlp",
+      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.24.mlp",
       "vision_tower.vision_model.encoder.layers.16.self_attn",
-      "vision_tower.vision_model.encoder.layers.10.mlp",
-      "vision_tower.vision_model.encoder.layers.7.mlp",
+      "vision_tower.vision_model.encoder.layers.19.mlp",
+      "vision_tower.vision_model.encoder.layers.20.mlp",
+      "language_model.model.layers.0.mlp",
+      "language_model.model.layers.2.self_attn",
+      "vision_tower.vision_model.encoder.layers.16.mlp",
       "vision_tower.vision_model.encoder.layers.14.mlp",
       "vision_tower.vision_model.encoder.layers.14.self_attn",
-      "vision_tower.vision_model.encoder.layers.9.mlp",
       "vision_tower.vision_model.encoder.layers.12.mlp",
-      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.13.mlp",
+      "vision_tower.vision_model.encoder.layers.10.mlp",
+      "vision_tower.vision_model.encoder.layers.11.self_attn",
+      "vision_tower.vision_model.encoder.layers.7.mlp",
       "vision_tower.vision_model.encoder.layers.5.mlp",
+      "vision_tower.vision_model.encoder.layers.9.mlp",
       "vision_tower.vision_model.encoder.layers.11.mlp",
-      "vision_tower.vision_model.encoder.layers.10.self_attn",
       "vision_tower.vision_model.encoder.layers.8.mlp",
-      "vision_tower.vision_model.encoder.layers.8.self_attn",
       "vision_tower.vision_model.encoder.layers.13.self_attn",
-      "vision_tower.vision_model.encoder.layers.12.self_attn",
-      "vision_tower.vision_model.encoder.layers.11.self_attn",
-      "vision_tower.vision_model.encoder.layers.4.mlp",
+      "vision_tower.vision_model.encoder.layers.9.self_attn",
+      "vision_tower.vision_model.encoder.layers.3.mlp",
+      "vision_tower.vision_model.encoder.layers.10.self_attn",
       "vision_tower.vision_model.encoder.layers.4.self_attn",
+      "vision_tower.vision_model.encoder.layers.4.mlp",
       "vision_tower.vision_model.encoder.layers.6.mlp",
-      "vision_tower.vision_model.encoder.layers.9.self_attn",
-      "vision_tower.vision_model.encoder.layers.2.mlp",
-      "vision_tower.vision_model.encoder.layers.7.self_attn",
       "vision_tower.vision_model.encoder.layers.1.mlp",
-      "vision_tower.vision_model.encoder.layers.3.mlp",
+      "vision_tower.vision_model.encoder.layers.8.self_attn",
+      "vision_tower.vision_model.encoder.layers.7.self_attn",
+      "vision_tower.vision_model.encoder.layers.12.self_attn",
       "vision_tower.vision_model.encoder.layers.1.self_attn",
-      "vision_tower.vision_model.encoder.layers.5.self_attn",
       "vision_tower.vision_model.encoder.layers.6.self_attn",
+      "vision_tower.vision_model.encoder.layers.2.mlp",
+      "vision_tower.vision_model.encoder.layers.5.self_attn",
       "vision_tower.vision_model.encoder.layers.3.self_attn",
       "vision_tower.vision_model.encoder.layers.0.self_attn",
-      "vision_tower.vision_model.encoder.layers.2.self_attn",
       "vision_tower.vision_model.encoder.layers.0.mlp",
+      "vision_tower.vision_model.encoder.layers.2.self_attn",
       "vision_tower.vision_model.encoder.layers.26.mlp"
     ],
     "llm_int8_threshold": 6.0,
@@ -125,7 +123,7 @@
     "vocab_size": 262208
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.50.0.dev0",
+  "transformers_version": "4.51.0",
   "unsloth_fixed": true,
   "vision_config": {
     "attention_dropout": 0.0,

generation_config.json

@@ -1,8 +1,13 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 2,
   "cache_implementation": "hybrid",
-  "eos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
   "pad_token_id": 0,
-  "transformers_version": "4.50.0.dev0"
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.51.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1d6b800fcac4ef0179121d62afd6fdc67b173aaebd36bf4a5cef970f3e44f31
-size 4437712953
+oid sha256:372535c95c031316bee6050d3d4ed6f9a2f991ee391c7da4bd40b38ca13e90d0
+size 4375543541