Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00010-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00011-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00012-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00012.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,31 @@
+---
+language: en
+pipeline_tag: text-generation
+tags:
+- safetensors
+---
+
+An experimental ablation of Gemma-3-27B-it, using the [Heretic](https://github.com/p-e-w/heretic) tool.
+
+Compared to the standard configuration of Heretic, there are a few changes:
+1. The training and test datasets used were extended compared to the default subset used by Heretic
+2. A version of [Magnitude-Preserving Orthogonal Ablation](https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration) (MPOA) is used
+3. To stay faithful to MPOA, the harmful direction to ablate is chosen from between 2 layers (Heretic's "global" direction scope)
+4. To stay faithful to MPOA, a 99% winsorization is applied to the residuals
+5. Some additional refusal markers were added to avoid bypassing the refusal detection with bad punctuation
+
+To achieve strong results:
+1. Parameter ranges were iteratively refined by looking at resulting refusal and divergence scores
+2. The scoring function was adjusted to prioritize low-refusal results
+
+The model name contains the properties of the ablation:
+1. `MPOA` for the usage of Magnitude-Preserving Orthogonal Ablation
+2. `G` for the usage of global direction scope
+3. `W` for the usage of winsorization
+4. `D` for the measured KL divergence
+5. `R` for the number of refusals
+
+Original: https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.1099-R01  
+GGUF (standard): https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.1099-R01-GGUF  
+GGUF (imatrix): https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.1099-R01-i1-GGUF  
+MLX: https://huggingface.co/spikymoth/G3-Heresy-MPOA-G-W99-D0.1099-R01-MLX

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "head_dim": 128,
+    "hidden_size": 5376,
+    "intermediate_size": 21504,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 16,
+    "query_pre_attn_scalar": 168,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "sliding_window": 1024
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da0290139f018bdea488b556c136d0f0ca4506fe5f5555cd97c0f6f2e886add
+size 4854573696

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf17dbadf9c7cd696e4768639601c3300ea659e49f018000956078cefd475cdf
+size 4954792944

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12b9d629d07b4583e19a467713f92b5c1ae8c9d7ef11faf1bdb91c4c7b59efc
+size 4954792976

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7171ed512e46c90cb579a58f66851bad09b028220422ceb1ae85080ab4ffb958
+size 4954793016

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb9667695749e55d808f407d78f18f80bd8ff999175c2c480cad7075ff5b2cf
+size 4954793016

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62ff81622c0c3c469eb1046794e10def21069869eec3cb391bed56e9cdaab26
+size 4954793016

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b663884e4087e1821e8d6202207886585c2cd15e003ac4c65c5d5d86a1067a4
+size 4954793016

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ae1e767076c159141fff3921302d3b529c0dca991b431469ea2cd2c7ded755
+size 4954793016

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123f66d85329ab75751b302dcf23875855a3266899399947da3b8d8b5a4d85e2
+size 4954793016

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702063d5db77241cef84a2f0ceafdadce3b0ae5edbced2488dc99e89be82b40d
+size 4954793016

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a94ad1e5a41143d2e1f2b38551fbc64a94d372101b976ca9384a903151e2d5
+size 4954793016

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f4d0c537a889d474396c6fb21ebb90946a64d70345403d47627ecb559e8e91
+size 462476696

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074