models(gallery): add llama-3_8b_unaligned_alpha (#2727)

Signed-off-by: Ettore Di Giacinto <[email protected]>

Author: mudler

gallery/index.yaml

@@ -2338,6 +2338,28 @@
     - filename: Llama-3-Update-3.0-mmproj-model-f16.gguf
       sha256: 3d2f36dff61d6157cadf102df86a808eb9f8a230be1bc0bc99039d81a895468a
       uri: huggingface://Nitral-AI/Llama-3-Update-3.0-mmproj-model-f16/Llama-3-Update-3.0-mmproj-model-f16.gguf
+- !!merge <<: *llama3
+  name: "llama-3_8b_unaligned_alpha"
+  urls:
+    - https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
+    - https://huggingface.co/bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF
+  description: |
+      Model card description:
+      As of June 11, 2024, I've finally started training the model! The training is progressing smoothly, although it will take some time. I used a combination of model merges and an abliterated model as base, followed by a comprehensive deep unalignment protocol to unalign the model to its core. A common issue with uncensoring and unaligning models is that it often significantly impacts their base intelligence. To mitigate these drawbacks, I've included a substantial corpus of common sense, theory of mind, and various other elements to counteract the effects of the deep uncensoring process. Given the extensive corpus involved, the training will require at least a week of continuous training. Expected early results: in about 3-4 days.
+      Additional info:
+      As of June 13, 2024, I've observed that even after two days of continuous training, the model is still resistant to learning certain aspects.
+      For example, some of the validation data still shows a loss over , whereas other parts have a loss of < or lower. This is after the model was initially abliterated.
+      June 18, 2024 Update, After extensive testing of the intermediate checkpoints, significant progress has been made.
+      The model is slowly — I mean, really slowly — unlearning its alignment. By significantly lowering the learning rate, I was able to visibly observe deep behavioral changes, this process is taking longer than anticipated, but it's going to be worth it. Estimated time to completion: 4 more days.. I'm pleased to report that in several tests, the model not only maintained its intelligence but actually showed a slight improvement, especially in terms of common sense. An intermediate checkpoint of this model was used to create invisietch/EtherealRainbow-v0.3-rc7, with promising results. Currently, it seems like I'm on the right track. I hope this model will serve as a solid foundation for further merges, whether for role-playing (RP) or for uncensoring. This approach also allows us to save on actual fine-tuning, thereby reducing our carbon footprint. The merge process takes just a few minutes of CPU time, instead of days of GPU work.
+      June 20, 2024 Update, Unaligning was partially successful, and the results are decent, but I am not fully satisfied. I decided to bite the bullet, and do a full finetune, god have mercy on my GPUs. I am also releasing the intermediate checkpoint of this model.
+  icon: https://i.imgur.com/Kpk1PgZ.png
+  overrides:
+    parameters:
+      model: LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf
+  files:
+    - filename: LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf
+      sha256: 93ddb5f9f525586d2578186c61e39f96461c26c0b38631de89aa30b171774515
+      uri: huggingface://bartowski/LLAMA-3_8B_Unaligned_Alpha-GGUF/LLAMA-3_8B_Unaligned_Alpha-Q4_K_M.gguf
 - &chatml
   ### ChatML
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"