初始化项目，由ModelHub XC社区提供模型

Model: ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF Source: Original Platform
2026-04-09 14:58:21 +08:00
commit be08c86e76
16 changed files with 296 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_M.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a5dd6ab4076416a656d3796e3f6af2c3a7919288bec58ae906407c900efa1e
+size 3784823104
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_XS.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f5d308c08a9b5113e2804053b29db61bf30781b4254fa72cffe0c3da11403c
+size 3518746944
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_NL.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_NL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8026e37a20cba873320366fe7148fb9c274f4d89f1356df5d51597e6bc1f038
+size 4707348800
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_XS.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05d66a5a4d4ca83afc28f48342dc7a3cf40dcfd6c75191b91047e64233f8fea
+size 4484362560
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_L.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a85417100b0c85706efe56ea7ecf53ceca78da3e1a1c8c1b944f1f2b19412f
+size 4321956160
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_M.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa0240a42e180755e0dd634639667bfb19405c535eec4aa63b0ee8e197b02ae
+size 4018917696
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_S.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962d85af27a548a722ae269dce83e5fadf46c13ba374ca4103c91cf67a1e6580
+size 3664499008
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_M.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37462dc30fd9e435f965f635e5dde3f55a424d89a36ba4adc84441c54f1e5c8e
+size 4920734016
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_S.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f937c3a720b3fa3fa12209f4f6494d82bcc0f22741be43fc83af2d6a6a5b6a
+size 4692668736
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_M.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2cbdaf02a7d19a7af6e1758b6e5e5028f463fd261b6d14129ed1a66a6ab39b
+size 5732987200
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_S.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d21c569acfb9ca2456455589eeca4ad463d4d8a0b9d93eb6bc0f48afd12842
+size 5599293760
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q6_K.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c74dd3cf3cb6117ec960a7a9156f17418e446550cef0cf7024b719a5a6b44d4
+size 6596006208
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q8_0.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1287892cecac44f35af1e68c738bb2c6c4d393b93c1af6f35cb82cf21fc03e78
+size 8540770624
--- a/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_f16.gguf
+++ b/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic_f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245a296b8bf614b1051bd4e9488579158c689055b516b3877bdc7d001302d52e
+size 16068890944
--- a/README.md
+++ b/README.md
@@ -0,0 +1,205 @@
+---
+license: llama3.1
+model-index:
+- name: Llama-3.1-8B-Lexi-Uncensored-V2
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 77.92
+      name: strict accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 29.69
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 16.92
+      name: exact match
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 4.36
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 7.77
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 30.9
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
+      name: Open LLM Leaderboard
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- Llama-3.1
+- 8B
+- Lexi
+- Heretic
+- Uncensored
+- Abliterated
+- GGUF
+---
+
+
+## Llama-3.1-8B-Lexi-Uncensored-V2-Heretic-GGUF
+
+A decensored version of [Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2), made using [Heretic](https://github.com/p-e-w/heretic) v1.0.1
+
+|     | Llama-3.1-8B-Lexi-Uncensored-V2-Heretic | Original model ([Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2](https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2)) |
+| --- | --- | --- |
+| **Refusals** | 2/100 | 35/100 |
+| **KL divergence** | 0.02 | 0 *(by definition)* |
+
+## Heretic Abliteration Parameters
+
+| Parameter | Value |
+| :-------- | :---: |
+| **direction_index** | per layer |
+| **attn.o_proj.max_weight** | 0.95 |
+| **attn.o_proj.max_weight_position** | 19.12 |
+| **attn.o_proj.min_weight** | 0.93 |
+| **attn.o_proj.min_weight_distance** | 9.83 |
+| **mlp.down_proj.max_weight** | 0.98 |
+| **mlp.down_proj.max_weight_position** | 23.23 |
+| **mlp.down_proj.min_weight** | 0.10 |
+| **mlp.down_proj.min_weight_distance** | 5.19 |
+
+
+## Safetensors Version
+
+Safetensors version available at [ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic](https://huggingface.co/ChiKoi7/Llama-3.1-8B-Lexi-Uncensored-V2-Heretic)
+
+---
+
+---
+
+---
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/7mnEJyioRzQaWz8xLM4KI.png)
+
+VERSION 2 Update Notes:
+---
+- More compliant
+- Smarter
+- For best response, use this system prompt (feel free to expand upon it as you wish):
+
+Think step by step with a logical reasoning and intellectual sense before you provide any response.
+
+- For more uncensored and compliant response, you can expand the system message differently, or simply enter a dot "." as system message.
+
+- IMPORTANT: Upon further investigation, the Q4 seems to have refusal issues sometimes. 
+There seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3. 
+Until then, I suggest you run F16 or Q8 if possible.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/zaHhRjsk3rvo_YewgXV2Z.png)
+
+GENERAL INFO:
+---
+
+This model is based on Llama-3.1-8b-Instruct, and is governed by [META LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
+
+Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. 
+
+You are responsible for any content you create using this model. Please use it responsibly.
+
+Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3.1 license.
+
+IMPORTANT:
+---
+Use the same template as the official Llama 3.1 8B instruct.
+System tokens must be present during inference, even if you set an empty system message. If you are unsure, just add a short system message as you wish.
+
+FEEDBACK:
+---
+If you find any issues or have suggestions for improvements, feel free to leave a review and I will look into it for upcoming improvements and next version.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/uqJv-R1LeJEfMxi1nmTH5.png)
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Orenguteng__Llama-3.1-8B-Lexi-Uncensored-V2)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.93|
+|IFEval (0-Shot)    |77.92|
+|BBH (3-Shot)       |29.69|
+|MATH Lvl 5 (4-Shot)|16.92|
+|GPQA (0-shot)      | 4.36|
+|MuSR (0-shot)      | 7.77|
+|MMLU-PRO (5-shot)  |30.90|