Upload folder using huggingface_hub

README.md

@@ -10,7 +10,7 @@ tags:
 library_name: peft
 ---
 
-# Harry Potter Multi-Persona QA Model (LoRA Adapter)
+# Harry Potter Multi-Persona QA Model V2 with 60K QA SFT (LoRA Adapter)
 
 This is a LoRA adapter for **google/gemma-2b** fine-tuned for Harry Potter universe question-answering with multiple character personas.
 
@@ -18,7 +18,7 @@ This is a LoRA adapter for **google/gemma-2b** fine-tuned for Harry Potter unive
 - **Hermione Granger**: Analytical, articulate, and deeply knowledgeable
 - **Harry Potter**: Courageous, emotional, and direct
 - **Severus Snape**: Cold, precise, and cutting
-- **Voldemort**: Grandiose, manipulative, and authoritative  
+- **Voldemort**: Grandiose, manipulative, and authoritative
 - **David Goggins**: Raw, gritty, and brutally honest
 - **Donald Trump**: Boastful, blunt, and repetitive
 - **General**: Expert on Harry Potter universe

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "gate_proj",
+    "down_proj",
     "up_proj",
     "o_proj",
-    "down_proj",
-    "v_proj",
     "q_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc6cede5d63a38c21ffbfa35265e45bc9bd0ab6e0e2b30379d1edda1e75c026
+oid sha256:f840361f07eb61471aa14253628f1bad50292ecb5bea12d934dd4a16cb52cc3d
 size 313820248

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c205986a2dbec95f525e7bd1344013285dcc42e5059ebacfbcc86ca01fc6dd15
+oid sha256:5473c9f5f84e8b6754dc97843a027f6ae0857633c87ba116d7d9610bf934e1df
 size 5752