(Trained with Unsloth)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.last and system_message is defined %}\n            {{- '[INST]' + system_message + '\\n\\n' }}\n        {%- else %}\n            {{- '[INST]' }}\n        {%- endif %}\n        {%- if message['content'] is not string %}\n            {%- for chunk in message['content'] %}\n                {%- if chunk['type'] == 'text' %}\n                    {{- chunk['text'] }}\n                {%- elif chunk['type'] == 'image' %}\n                    {{- '[IMG]' }}\n                {%- else %}\n                    {{- raise_exception('Unrecognized content type!') }}\n                {%- endif %}\n            {%- endfor %}\n        {%- else %}\n            {{- message['content'] }}\n        {%- endif %}\n        {{- '[/INST]' }}\n    {%- elif message['role'] == 'assistant' %}\n        {{- message['content'][0]['text'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}"
+}

config.json

@@ -0,0 +1,54 @@
+{
+    "architectures": [
+        "LlavaForConditionalGeneration"
+    ],
+    "ignore_index": -100,
+    "image_seq_length": 1,
+    "image_token_index": 10,
+    "model_type": "llava",
+    "multimodal_projector_bias": true,
+    "pad_token_id": 11,
+    "projector_hidden_act": "gelu",
+    "text_config": {
+        "attention_dropout": 0.0,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "intermediate_size": 14336,
+        "max_position_embeddings": 1024000,
+        "model_type": "mistral",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 8,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": null,
+        "rope_theta": 1000000000.0,
+        "sliding_window": null,
+        "torch_dtype": "float16",
+        "use_cache": true,
+        "vocab_size": 131072
+    },
+    "torch_dtype": "float16",
+    "transformers_version": "4.51.1",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.4.3",
+    "vision_config": {
+        "attention_dropout": 0.0,
+        "head_dim": 64,
+        "hidden_act": "gelu",
+        "hidden_size": 1024,
+        "image_size": 1024,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "model_type": "pixtral",
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "num_hidden_layers": 24,
+        "patch_size": 16,
+        "rope_theta": 10000.0,
+        "torch_dtype": "float16"
+    },
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "full"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 11,
+  "transformers_version": "4.51.1"
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,8 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 16,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 1
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019ee67e9f48e7ea1fb4e17f731ebb7735fd25a3d51b18cb5dd0e11999574f55
+size 17077428