Upload model

README.md

@@ -1,4 +1,7 @@
 ---
+{}
+---
+---
 library_name: transformers
   pipeline_tag: image-text-to-text
   tags:

adapter_config.json

@@ -4,8 +4,7 @@
   "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "DeepseekOCR2ForCausalLM",
-    "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2",
-    "unsloth_fixed": true
+    "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
   },
   "base_model_name_or_path": "./deepseek_ocr2",
   "bias": "none",
@@ -20,9 +19,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -32,12 +31,17 @@
   "r": 32,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|qkv|proj|lin1|lin2).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|qkv|proj|lin1|lin2)))",
-  "target_parameters": [
-    "mlp.experts.gate_up_proj",
-    "mlp.experts.down_proj"
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "target_parameters": null,
+  "task_type": null,
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44827d1a99a988512419a1a29e2aae9a17cfbe121938595950c0144c4b03acba
-size 18863392
+oid sha256:d3da86e8684d15d20b536dbe1a8cc81d8b00238dcd0952b3a4dd8fcc8c3dcf3b
+size 691141456