Upload fine-tune model from Kaggle

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.1-8B-Instruct
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
 library_name: peft
 ---
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -14,7 +14,7 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "o_proj",
+    "v_proj",
     "down_proj",
     "k_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78fc62dade2160d27173f10d0d1a528eb760a8dafa85769a001daf755c8fc6d6
+oid sha256:ca6892518b24d84f27d0315e37003c063e4f288f663cfe7679bfed73710225ae
 size 671149168

special_tokens_map.json

@@ -13,5 +13,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:384a7e7c676f7be2e5d2e8449c508be9b00e5b18c5b3c39ebc626e96b3f4b988
+size 17210019

tokenizer_config.json

@@ -2059,6 +2059,7 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|eot_id|>",
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }