Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
 license: llama3.2
-base_model: meta-llama/Llama-3.2-11B-Vision-Instruct
+base_model: meta-llama/Llama-3.2-90B-Vision-Instruct
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # text
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-90B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct) on the None dataset.
 
 ## Model description
 
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.3
+- PEFT 0.14.0
+- Transformers 4.48.1
 - Pytorch 2.5.1+cu124
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -4,8 +4,10 @@
     "base_model_class": "MllamaForConditionalGeneration",
     "parent_library": "transformers.models.mllama.modeling_mllama"
   },
-  "base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-90B-Vision-Instruct",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": "gaussian",
@@ -14,6 +16,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 8,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "down_proj",
-    "q_proj",
+    "up_proj",
     "k_proj",
+    "q_proj",
     "o_proj",
-    "up_proj"
+    "v_proj",
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72d5ec5c5d9ce352b7522e7ec6867c0fe6f74427695c7bc2efb9891c7a5d3ed
-size 125866776
+oid sha256:9895f41d607f56831abd6ef097d101a35e9a73e13090b20c456abce4180d9195
+size 565641552

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf4e3e23fabe472d5990932d00b0ebdb8bfaa4a5a69825173a97d64f8211531
-size 5240
+oid sha256:7e920ae8d3f2a036f0f511582177ae84b3e39f82af7a5199c516e3ad1c31151e
+size 5304