(Trained with Unsloth)

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit",
+  "architectures": [
+    "MllamaForConditionalGeneration"
+  ],
+  "image_token_index": 128256,
+  "model_type": "mllama",
+  "pad_token_id": 128004,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "model_type": "mllama_text_model",
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "torch_dtype": "float16"
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.49.0.dev0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.2.5",
+  "vision_config": {
+    "image_size": 560,
+    "model_type": "mllama_vision_model",
+    "torch_dtype": "float16"
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.49.0.dev0"
+}