Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: llama3.2
-base_model: alpindale/Llama-3.2-11B-Vision-Instruct
+base_model: Kendamarron/Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora
 
-This model is a fine-tuned version of [alpindale/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/alpindale/Llama-3.2-11B-Vision-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Kendamarron/Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge](https://huggingface.co/Kendamarron/Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge) on an unknown dataset.
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 1
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "MllamaForConditionalGeneration",
     "parent_library": "transformers.models.mllama.modeling_mllama"
   },
-  "base_model_name_or_path": "alpindale/Llama-3.2-11B-Vision-Instruct",
+  "base_model_name_or_path": "Kendamarron/Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -27,12 +27,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "up_proj",
+    "gate_proj",
     "down_proj",
-    "k_proj",
+    "q_proj",
     "o_proj",
-    "gate_proj"
+    "k_proj",
+    "up_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df8be3d456dcc78d7ad14050738589f046087b89f227f8e1da5ec26e032ee4b
+oid sha256:243d30a92ab2c69c6ebfc3e3822666593614ac485e4d253cd85dcdda4c4ac25d
 size 125866776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d23a1f32ab6bce0f981768bbac4bf8756b5e2cc4c71db976163be7a16401af7
+oid sha256:0a6e67a4a322b46ca40edd02fa7854e9b0bedb8e168b6cc5ad02c5482bc97734
 size 5304