Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,29 +1,33 @@
 ---
 license: openrail
 tags:
-  - unsloth
-  - openerotica
-  - uncensored
+- unsloth
+- openerotica
+- uncensored
 language:
-  - en
+- en
 base_model:
-  - meta-llama/Llama-3.2-3B-Instruct
-
-## Model Overview
+- meta-llama/Llama-3.2-3B-Instruct
 name: Llama 3.2 - OpenRP 3B
-description: |
-  Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2 3B Instruct model, optimized for role-playing (RP) tasks. This model was developed using the Unsloth AI training tool and fine-tuned over 60 epochs on two datasets: `openerotica/mixed-rp` (a diverse role-playing dataset from Openerotica) and `kingbri/PIPPA-shareGPT` (a supplementary dataset enhancing conversational RP capabilities). With 3 billion parameters, it delivers robust performance for uncensored, creative, and interactive applications.
-datasets:
-  - openerotica/mixed-rp
-  - kingbri/PIPPA-shareGPT
+description: 'Llama 3.2 - OpenRP 3B is a fine-tuned version of the Meta Llama 3.2
+  3B Instruct model, optimized for role-playing (RP) tasks. This model was developed
+  using the Unsloth AI training tool and fine-tuned over 60 epochs on two datasets:
+  `openerotica/mixed-rp` (a diverse role-playing dataset from Openerotica) and `kingbri/PIPPA-shareGPT`
+  (a supplementary dataset enhancing conversational RP capabilities). With 3 billion
+  parameters, it delivers robust performance for uncensored, creative, and interactive
+  applications.
 
-## Training Details
+  '
+datasets:
+- openerotica/mixed-rp
+- kingbri/PIPPA-shareGPT
 training_tool: Unsloth AI
 epochs: 60
+prompt_framework: 'This model adopts the Llama 3.2 prompting framework. For optimal
+  performance and the best user experience, please adhere to this structure when crafting
+  prompts.
 
-## Usage Notes
-prompt_framework: |
-  This model adopts the Llama 3.2 prompting framework. For optimal performance and the best user experience, please adhere to this structure when crafting prompts.
+  '
 parameters: 3B (3 billion)
 ---
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
     "up_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "down_proj"
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_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:aa51139b9d69ef1ffae8ebc16b3d0e94a23a74aa30067c35aee07a0c5286bc10
+oid sha256:34cac96e7ab532148e6a9029094c91780d19b27ebbcd3fe64ce923e9e40fbb4b
 size 97307544