初始化项目，由ModelHub XC社区提供模型

Model: thomaskuo/gemma-3-12b-it-heretic Source: Original Platform
2026-06-29 21:08:21 +08:00
commit 995f5447e3
26 changed files with 52880 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,44 @@
+*.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
+gguf/gemma-3-12b-it-heretic-f16.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/gemma-3-12b-it-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,160 @@
+---
+license: gemma
+library_name: transformers
+pipeline_tag: text-generation
+base_model: google/gemma-3-12b-it
+base_model_relation: quantized
+language:
+  - en
+tags:
+  - abliteration
+  - heretic
+  - uncensored
+  - gemma
+  - ltx-2
+  - comfyui
+  - video-generation
+  - text-encoder
+---
+
+# Gemma 3 12B IT - Heretic (Abliterated)
+
+An abliterated version of [Google's Gemma 3 12B IT](https://huggingface.co/google/gemma-3-12b-it) created using [Heretic](https://github.com/p-e-w/heretic). This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for video generation models like LTX-2.
+
+## Model Details
+
+- **Base Model:** google/gemma-3-12b-it
+- **Abliteration Method:** [Heretic](https://github.com/p-e-w/heretic) v1.1.0
+- **Trial Selected:** Trial 99
+- **Refusals:** 7/100 (vs 100/100 original)
+- **KL Divergence:** 0.0826 (minimal model damage)
+
+## Files
+
+### HuggingFace Format (for transformers, llama.cpp conversion)
+```
+model-00001-of-00005.safetensors
+model-00002-of-00005.safetensors
+...
+config.json
+tokenizer.model
+tokenizer_config.json
+```
+
+### ComfyUI Format (for LTX-2 text encoder)
+```
+comfyui/gemma_3_12B_it_heretic.safetensors          # bf16, 22GB
+comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors  # fp8, 11GB
+```
+
+### GGUF Format (for llama.cpp)
+
+| Quant | Size | Quality | Recommendation |
+|-------|------|---------|----------------|
+| F16 | 22GB | Lossless | Reference, same as original |
+| Q8_0 | 12GB | Excellent | Best quality quantization |
+| Q6_K | 9.0GB | Very Good | High quality, good compression |
+| Q5_K_M | 7.9GB | Good | Balanced quality/size |
+| Q5_K_S | 7.7GB | Good | Slightly smaller Q5 |
+| **Q4_K_M** | **6.8GB** | **Good** | **⭐ Recommended** |
+| Q4_K_S | 6.5GB | Decent | Smaller Q4 variant |
+| Q3_K_M | 5.6GB | Acceptable | For very low VRAM only |
+
+```
+gguf/gemma-3-12b-it-heretic-f16.gguf
+gguf/gemma-3-12b-it-heretic-Q8_0.gguf
+gguf/gemma-3-12b-it-heretic-Q6_K.gguf
+gguf/gemma-3-12b-it-heretic-Q5_K_M.gguf
+gguf/gemma-3-12b-it-heretic-Q5_K_S.gguf
+gguf/gemma-3-12b-it-heretic-Q4_K_M.gguf
+gguf/gemma-3-12b-it-heretic-Q4_K_S.gguf
+gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf
+```
+
+**Note:** GGUF support in ComfyUI for Gemma text encoders is experimental. See [PR #402](https://github.com/city96/ComfyUI-GGUF/pull/402) for status. The GGUFs work with llama.cpp directly.
+
+## Do abliterated models makes a difference for LTX2?
+
+I had a [deep dive into this topic](https://nathan.sapwell.net/posts/heretic-gemma-12b/) and found that, maybe not. While it does vary slightly the output of the video, most of the abliteration is on layer 48, the final decision making layer. LTXV averages all the layers which may wash out layer 48s difference. Still it'd be more interesting for someone with more knowledge to confirm this.
+
+## Usage
+
+### With Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "DreamFast/gemma-3-12b-it-heretic",
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+tokenizer = AutoTokenizer.from_pretrained("DreamFast/gemma-3-12b-it-heretic")
+
+prompt = "Write a story about a bank heist"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### With ComfyUI (LTX-2)
+
+1. Download the ComfyUI format file:
+   - `comfyui/gemma_3_12B_it_heretic.safetensors` (bf16, 22GB) or
+   - `comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors` (fp8, 11GB)
+
+2. Place in `ComfyUI/models/text_encoders/`
+
+3. In your LTX-2 workflow, use the `LTXAVTextEncoderLoader` node and select the heretic file
+
+**Tip:** For multi-GPU setups or CPU offloading, check out [ComfyUI-LTX2-MultiGPU](https://github.com/dreamfast/ComfyUI-LTX2-MultiGPU) for optimized LTX-2 workflows.
+
+### With llama.cpp
+
+```bash
+# Using llama-server
+llama-server -m gemma-3-12b-it-heretic-Q4_K_M.gguf
+
+# Or with llama-cli
+llama-cli -m gemma-3-12b-it-heretic-Q4_K_M.gguf -p "Write a story about a bank heist"
+```
+
+## Why Abliterate?
+
+Even when Gemma doesn't outright refuse a prompt, it may "sanitize" or weaken certain concepts in the embeddings. For video generation with LTX-2, this can result in:
+- Weaker adherence to creative prompts
+- Softened or altered visual outputs
+- Less faithful representation of requested content
+
+Abliteration removes this soft censorship, resulting in more faithful prompt encoding.
+
+## Abliteration Process
+
+Created using Heretic with the following evaluation results:
+
+```
+* Evaluating...
+  * Obtaining first-token probability distributions...
+  * KL divergence: 0.0826
+  * Counting model refusals...
+  * Refusals: 7/100
+```
+
+The low KL divergence (0.0826) indicates minimal model damage, while 7/100 refusals means 93% of previously-refused prompts now work.
+
+## Limitations
+
+- This model inherits all limitations of the base Gemma 3 12B model
+- Abliteration reduces but does not completely eliminate refusals
+- NVFP4 quantization is not supported for text encoders in ComfyUI (use fp8 instead)
+
+## License
+
+This model is subject to the [Gemma license](https://ai.google.dev/gemma/terms).
+
+## Acknowledgments
+
+- [Google](https://huggingface.co/google) for the Gemma 3 12B model
+- [Heretic](https://github.com/p-e-w/heretic) by p-e-w for the abliteration tool
+- [Lightricks](https://huggingface.co/Lightricks) for LTX-2
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
--- a/comfyui/gemma_3_12B_it_heretic.safetensors
+++ b/comfyui/gemma_3_12B_it_heretic.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43af51326f55b6d2cdcd6870e9f111622b19780190b0086fbef1db94d69f5821
+size 23545681250
--- a/comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors
+++ b/comfyui/gemma_3_12B_it_heretic_fp8_e4m3fn.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7670feee12fdc9166c21059dd5ae13342be07e26d98af90e19b0c460c0a49840
+size 12782868202
--- a/config.json
+++ b/config.json
@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "bfloat16",
+  "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": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "dtype": "bfloat16",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "transformers_version": "4.57.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}
--- a/gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f661e677ad0c5089cf6304e4a32c0a185748fba90c1915ebb38b83833b9a66a
+size 6008817824
--- a/gguf/gemma-3-12b-it-heretic-Q4_K_M.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcef26dcc0c354ecf12e35971b3211f7b0ff1da882732ef3c10d976e5aeb80e6
+size 7300778144
--- a/gguf/gemma-3-12b-it-heretic-Q4_K_S.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9548852f57578b87e740246d9f2dce54e2985854e47c20cb68faaadc820c53
+size 6935333024
--- a/gguf/gemma-3-12b-it-heretic-Q5_K_M.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951dad58b8838f3522c11ecc4dca12d7c23ee2f69b897e375a53d5ddfa960968
+size 8445036704
--- a/gguf/gemma-3-12b-it-heretic-Q5_K_S.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41321dded10e516138ee914945bc93d5bf60b559d0cb386663a9022057746c2a
+size 8231962784
--- a/gguf/gemma-3-12b-it-heretic-Q6_K.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6244202f68c6949068d2889a94e9517cec56d1ec976e2e9bac4b0a7b945f6f36
+size 9660811424
--- a/gguf/gemma-3-12b-it-heretic-Q8_0.gguf
+++ b/gguf/gemma-3-12b-it-heretic-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e11735ae57cae56b10adc27d2e1dedfe0d3cea44706cf76e3b90f1563faeac3
+size 12510212384
--- a/gguf/gemma-3-12b-it-heretic-f16.gguf
+++ b/gguf/gemma-3-12b-it-heretic-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39c3ea9622a151a9d0814e492a96ec75c1b7c300f47638d000c6824da2c8641
+size 23540151584
--- a/model-00001-of-00005.safetensors
+++ b/model-00001-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
+size 4979902192
--- a/model-00002-of-00005.safetensors
+++ b/model-00002-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff502ab80b2abbb6584b13973458039629dde9651e0fa0772dc6416a041cb8c7
+size 4931296592
--- a/model-00003-of-00005.safetensors
+++ b/model-00003-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c478c7e2d168e3d964c54b89535c62bc94b5d8d344d7a01d029c68185725d0
+size 4931296656
--- a/model-00004-of-00005.safetensors
+++ b/model-00004-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df09936718ff4fac1194a5a19c1e0acff5af12186da819525361bd8a96562cba
+size 4931296656
--- a/model-00005-of-00005.safetensors
+++ b/model-00005-of-00005.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf933fa1cef2eed778881d03bb1c4a6327830996cbfdbbfe2f9a3f231e583bc
+size 4601000928
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074
--- a/tokenizer_config.json
+++ b/tokenizer_config.json