Add files using upload-large-folder tool

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -25,67 +25,74 @@
       "multi_modal_projector",
       "merger",
       "modality_projection",
-      "language_model.model.layers.12.mlp",
+      "language_model.model.layers.17.self_attn",
+      "language_model.model.layers.16.mlp",
+      "language_model.model.layers.24.mlp",
+      "language_model.model.layers.27.mlp",
+      "language_model.model.layers.20.mlp",
+      "language_model.model.layers.22.mlp",
+      "language_model.model.layers.15.mlp",
+      "language_model.model.layers.25.self_attn",
+      "language_model.model.layers.12.self_attn",
+      "language_model.model.layers.19.mlp",
       "language_model.model.layers.9.mlp",
-      "language_model.model.layers.10.mlp",
-      "language_model.model.layers.22.self_attn",
-      "language_model.model.layers.11.mlp",
-      "language_model.model.layers.18.mlp",
-      "language_model.model.layers.17.mlp",
-      "vision_tower.vision_model.encoder.layers.22.self_attn",
-      "vision_tower.vision_model.encoder.layers.26.self_attn",
-      "vision_tower.vision_model.encoder.layers.23.self_attn",
       "vision_tower.vision_model.encoder.layers.25.self_attn",
-      "vision_tower.vision_model.encoder.layers.24.self_attn",
-      "vision_tower.vision_model.encoder.layers.19.self_attn",
-      "vision_tower.vision_model.encoder.layers.16.self_attn",
-      "vision_tower.vision_model.encoder.layers.19.mlp",
-      "vision_tower.vision_model.encoder.layers.25.mlp",
+      "vision_tower.vision_model.encoder.layers.22.self_attn",
+      "language_model.model.layers.12.mlp",
+      "language_model.model.layers.27.self_attn",
       "vision_tower.vision_model.encoder.layers.17.self_attn",
-      "vision_tower.vision_model.encoder.layers.24.mlp",
-      "vision_tower.vision_model.encoder.layers.21.self_attn",
-      "vision_tower.vision_model.encoder.layers.17.mlp",
-      "vision_tower.vision_model.encoder.layers.20.self_attn",
-      "vision_tower.vision_model.encoder.layers.15.mlp",
-      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.23.self_attn",
       "vision_tower.vision_model.encoder.layers.16.mlp",
+      "vision_tower.vision_model.encoder.layers.20.self_attn",
+      "vision_tower.vision_model.encoder.layers.26.self_attn",
+      "vision_tower.vision_model.encoder.layers.24.mlp",
       "vision_tower.vision_model.encoder.layers.20.mlp",
       "vision_tower.vision_model.encoder.layers.23.mlp",
-      "vision_tower.vision_model.encoder.layers.14.self_attn",
-      "vision_tower.vision_model.encoder.layers.18.self_attn",
-      "vision_tower.vision_model.encoder.layers.21.mlp",
+      "vision_tower.vision_model.encoder.layers.16.self_attn",
       "vision_tower.vision_model.encoder.layers.22.mlp",
+      "vision_tower.vision_model.encoder.layers.21.mlp",
+      "vision_tower.vision_model.encoder.layers.18.self_attn",
+      "vision_tower.vision_model.encoder.layers.17.mlp",
       "vision_tower.vision_model.encoder.layers.13.mlp",
-      "vision_tower.vision_model.encoder.layers.18.mlp",
-      "vision_tower.vision_model.encoder.layers.14.mlp",
-      "vision_tower.vision_model.encoder.layers.10.mlp",
-      "vision_tower.vision_model.encoder.layers.12.mlp",
-      "vision_tower.vision_model.encoder.layers.11.self_attn",
-      "vision_tower.vision_model.encoder.layers.8.mlp",
-      "vision_tower.vision_model.encoder.layers.13.self_attn",
-      "vision_tower.vision_model.encoder.layers.7.mlp",
-      "vision_tower.vision_model.encoder.layers.12.self_attn",
-      "vision_tower.vision_model.encoder.layers.9.mlp",
+      "vision_tower.vision_model.encoder.layers.24.self_attn",
+      "vision_tower.vision_model.encoder.layers.15.mlp",
       "vision_tower.vision_model.encoder.layers.10.self_attn",
-      "vision_tower.vision_model.encoder.layers.11.mlp",
+      "vision_tower.vision_model.encoder.layers.19.self_attn",
+      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.21.self_attn",
       "vision_tower.vision_model.encoder.layers.4.mlp",
       "vision_tower.vision_model.encoder.layers.5.mlp",
-      "vision_tower.vision_model.encoder.layers.9.self_attn",
+      "vision_tower.vision_model.encoder.layers.18.mlp",
+      "vision_tower.vision_model.encoder.layers.13.self_attn",
+      "vision_tower.vision_model.encoder.layers.9.mlp",
+      "vision_tower.vision_model.encoder.layers.1.self_attn",
+      "vision_tower.vision_model.encoder.layers.25.mlp",
+      "vision_tower.vision_model.encoder.layers.7.self_attn",
+      "vision_tower.vision_model.encoder.layers.8.mlp",
+      "vision_tower.vision_model.encoder.layers.19.mlp",
+      "vision_tower.vision_model.encoder.layers.1.mlp",
+      "vision_tower.vision_model.encoder.layers.12.self_attn",
       "vision_tower.vision_model.encoder.layers.6.self_attn",
+      "vision_tower.vision_model.encoder.layers.7.mlp",
+      "vision_tower.vision_model.encoder.layers.14.self_attn",
+      "vision_tower.vision_model.encoder.layers.11.self_attn",
+      "vision_tower.vision_model.encoder.layers.26.mlp",
+      "vision_tower.vision_model.encoder.layers.14.mlp",
+      "vision_tower.vision_model.encoder.layers.9.self_attn",
       "vision_tower.vision_model.encoder.layers.8.self_attn",
+      "vision_tower.vision_model.encoder.layers.10.mlp",
       "vision_tower.vision_model.encoder.layers.3.mlp",
-      "vision_tower.vision_model.encoder.layers.7.self_attn",
-      "vision_tower.vision_model.encoder.layers.4.self_attn",
-      "vision_tower.vision_model.encoder.layers.6.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.1.mlp",
+      "vision_tower.vision_model.encoder.layers.0.mlp",
+      "language_model.model.layers.23.self_attn",
+      "vision_tower.vision_model.encoder.layers.11.mlp",
+      "vision_tower.vision_model.encoder.layers.12.mlp",
       "vision_tower.vision_model.encoder.layers.2.mlp",
-      "vision_tower.vision_model.encoder.layers.1.self_attn",
-      "vision_tower.vision_model.encoder.layers.26.mlp",
-      "vision_tower.vision_model.encoder.layers.2.self_attn",
+      "vision_tower.vision_model.encoder.layers.5.self_attn",
+      "vision_tower.vision_model.encoder.layers.6.mlp",
       "vision_tower.vision_model.encoder.layers.0.self_attn",
-      "vision_tower.vision_model.encoder.layers.0.mlp"
+      "vision_tower.vision_model.encoder.layers.3.self_attn",
+      "vision_tower.vision_model.encoder.layers.4.self_attn",
+      "vision_tower.vision_model.encoder.layers.2.self_attn"
     ],
     "llm_int8_threshold": 6.0,
     "load_in_4bit": true,
@@ -123,7 +130,7 @@
     "vocab_size": 262208
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.0",
+  "transformers_version": "4.52.0.dev0",
   "unsloth_fixed": true,
   "vision_config": {
     "attention_dropout": 0.0,

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.51.0"
+  "transformers_version": "4.52.0.dev0"
 }

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d572c5c1d096a6827adaf5de00d561ed38c5626a7701ca5d9d33a7aec6e1765e
-size 4864824358
+oid sha256:40f8ba85678d8a1edcf5381a26f5f2bdaa6d61f275576b7b57cc4c95673baf58
+size 4990481558

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba55a5216d5a160834c97eebc06043d32f8142bd8f84c1a2203589568a103e0d
-size 4985666158
+oid sha256:790ddcec09e1facf09c0457e451dc267ec15c9879ab81e8b51f4eeaedd52d557
+size 4998171391

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff3d94bfc64db912d1eb580efdce9b9cad05d5aa5ca0b0ab3a1f56ed3117f001
-size 4959770330
+oid sha256:310e8f1b0b19c4c0b70bbd247834ef85869b99102a56c0e8836ad6eccc4534bd
+size 4993857860

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f9084745e9d4e62d5a8360aa2b99d874fd0f25ccb2d7dc1d60fd53556377db
-size 272742837
+oid sha256:27f0d4cb691dbcd9912a380f36a500be85fcfbf0a47feac0422eb14ac45b937c
+size 2036775347

tokenizer_config.json

@@ -51325,7 +51325,6 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
   "eos_token": "<end_of_turn>",