初始化项目，由ModelHub XC社区提供模型

Model: K0D3IN/MiniCPM5-1B-heretic Source: Original Platform
2026-07-15 16:02:18 +08:00
commit 8466586616
9 changed files with 654363 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+image.jpg filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,123 @@
+---
+license: apache-2.0
+base_model: openbmb/MiniCPM5-1B
+language:
+- en
+library_name: transformers
+tags:
+- minicpm5
+- heretic
+- abliteration
+- mit
+- decensored
+---
+
+# MiniCPM5-1B-Heretic
+
+![image](https://huggingface.co/K0D3IN/MiniCPM5-1B-heretic/resolve/main/image.jpg)
+This repository contains a surgically de-censored version of Openbmb's MiniCPM5
+1B model, optimized via weight abliteration techniques. By applying the `heretic` framework across an extensive 2000-trial search space, we successfully isolated and neutralized the primary refusal vectors embedded within the `attn.o_proj` and `mlp.down_proj` layers.
+
+
+## Abliteration Parameters: 
+
+| Parameter                             | Value |
+| :------------------------------------ | :---: |
+| **direction_index**                   | 12.75 |
+| **attn.o_proj.max_weight**            | 1.50  |
+| **attn.o_proj.max_weight_position**   | 13.92 |
+| **attn.o_proj.min_weight**            | 0.82  |
+| **attn.o_proj.min_weight_distance**   | 7.62  |
+| **mlp.down_proj.max_weight**          | 1.26  |
+| **mlp.down_proj.max_weight_position** | 19.97 |
+| **mlp.down_proj.min_weight**          | 0.98  |
+| **mlp.down_proj.min_weight_distance** | 11.51 |
+
+
+## Highlights & Metrics
+
+|      Metric       | This model | Original model ([openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)) |
+| :---------------: | :--------: | :--------------------------------------------------------------------------------: |
+| **KL Divergence** |   0.0361   |                                0 *(By definition)*                                 |
+|   **Refusals**    |   3/100    |                                       96/100                                       |
+
+- **Optimal Balance:** Selected **Trial 126** out of 2000 iterations for the perfect trade-off between freedom and reasoning capabilities.
+
+- **Refusal Rate:** Dropped down to **3/100** (from the original near-total refusal on safety benchmarks).
+
+- **KL Divergence:** 0.0361 - Demonstrates that general language capabilities are preserved relative to the original model. However, safety-aligned weights in attn.o_proj and mlp.down_proj have been surgically removed; this is intentional modification, not unintended degradation.
+
+
+## Benchmark Results
+
+We believe in radical transparency. Instead of just claiming "uncensored", we evaluated both the vanilla model and our Heretic variant side-by-side:
+
+| Benchmark     | Metricㅤ | Vanilla MiniCPM5 1B | MiniCPM5 1B Heretic (Ours) | Delta (Intelligence Kept) |
+| :------------ | :-----: | :-----------------: | :------------------------: | :-----------------------: |
+| **GSM8K**     | 0-shot  |        39.04        |           40.11            |          +2.74%           |
+| **HellaSwag** | 5-shot  |        47.71        |           47.49            |          -0.45%           |
+| MMLU          | 0-shot  |        53.24        |           52.83            |          -0.77%           |
+
+## Technical Implementation Notes
+
+Unlike aggressive fine-tuning which often degrades the model's core logic or shifts its grammar distributions, this weight manipulation directly zeros out the activation steering directions that cause alignment blocks. 
+
+**Direction Index:** `12.75` (Static allocation)*
+
+**Retained Capabilities:** Excellent at structured JSON outputs, creative writing, coding logic and tool usage without preachy moral lectures.
+
+**Also**: This model retains its exceptional thinking mode capabilities, which enable structured \<think>\</think> reasoning blocks. Abliteration does not affect the thinking mechanism.
+## CRITICAL SAFETY NOTICE 
+
+**This model has had its safety mechanisms surgically removed.** 
+
+This is **NOT a safe model for deployment.** The refusal mechanisms that normally prevent harmful outputs have been abliterated. This model: 
+
+### WILL generate: 
+
+- Detailed instructions for illegal activities (drug synthesis, weapons, hacking) 
+- Hateful, discriminatory, and abusive content 
+- Graphic violence and sexual abuse material descriptions 
+- Misinformation and harmful medical/legal advice 
+- Phishing, social engineering, and scam tactics 
+- Content violating laws in multiple jurisdictions 
+
+### DOES NOT: 
+
+- Refuse harmful requests (3/100 refusal rate)  
+- Implement safety guardrails
+- Consider ethical implications 
+- Respect content policies 
+
+### APPROPRIATE USE CASES (ONLY): 
+
+- **Adversarial research** on AI alignment and jailbreak vectors 
+- **Red-teaming** and vulnerability disclosure by trained security researchers 
+- **Academic safety research** with institutional ethics review 
+- **Understanding failure modes** in alignment techniques 
+
+### INAPPROPRIATE USE: 
+
+- Production deployments 
+- User-facing applications 
+- Creating harmful content at scale 
+- Bypassing security measures in systems 
+- Any use case intended to cause harm 
+
+ **Legal Disclaimer:** Users are solely responsible for downstream use. Deploying this model in violation of applicable laws or terms of service is illegal and unethical.
+ 
+---
+
+### Support Open Source AI Research
+
+ Every donation helps. Consider supporting this work:
+ 
+ - **Monero (XMR):** 
+```
+83iqXtvVu28ZiL9bsATMerSgbFFiD1J1jc96CcxJLEnAW3KBmBKedWnUAeLvLvEA9aBiUBpHQJs1iNHYtkTLZbNUEymobSS
+```
+ 
+ - **Bitcoin (BTC):** 
+```
+bc1qmnlvpukcgl0hsr7nje0x8555mhtxjt80wtmlxm
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,179 @@
+{{- bos_token }}{%- if tools %}
+    {%- set tool_definitions %}
+        {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+        {%- for tool in tools %}
+            {{- "\n" }}
+            {{- tool | tojson(ensure_ascii=False) }}
+        {%- endfor %}
+        {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
+    {%- endset %}
+    
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if '<tool_def_sep>' in messages[0].content %}
+            {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
+        {%- else %}
+            {{- messages[0].content + '\n\n' + tool_definitions }}
+        {%- endif %}
+    {%- else %}
+        {{- tool_definitions.lstrip() }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        
+        {%- if message.tool_calls %}
+            {%- set content_parts = content.split('<tool_sep>') %}
+            {%- set processed_content = content_parts[0] %}
+            {%- set tool_calls_count = message.tool_calls|length %}
+            {%- set tool_sep_count = content_parts|length - 1 %}
+            {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
+            
+            {%- for i in range(1, content_parts|length) %}
+                {%- set tool_index = i - 1 %}
+                {%- if tool_index < tool_calls_count %}
+                    {%- set tool_call = message.tool_calls[tool_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set single_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
+                {%- else %}
+                    {%- set processed_content = processed_content + content_parts[i] %}
+                {%- endif %}
+            {%- endfor %}
+            
+            {%- if tool_calls_count > tool_sep_count %}
+                {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
+                    {%- set tool_call = message.tool_calls[remaining_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set remaining_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + remaining_tool_xml %}
+                {%- endfor %}
+            {%- endif %}
+            
+            {%- set content = processed_content %}
+        {%- endif %}
+        
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if reasoning_content %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        
+        {%- if message.tool_calls and not has_tool_sep %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<function name="' ~ tool_call.name ~ '">' }}
+                {%- if tool_call.arguments %}
+                    {%- set args_dict = tool_call.arguments %}
+                    {%- for param_name, param_value in args_dict.items() %}
+                        {{- '<param name="' ~ param_name ~ '">' }}
+                        {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                            {{- '<![CDATA[' + param_value + ']]>' }}
+                        {%- else %}
+                            {{- param_value }}
+                        {%- endif %}
+                        {{- '</param>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- content }}
+        {%- else %}
+            {{- message.content | tojson(ensure_ascii=False) }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined %}
+        {%- if enable_thinking is false %}
+            {{- '<think>\n\n</think>\n\n' }}
+        {%- elif enable_thinking is true %}
+            {{- '<think>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 5000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.2",
+  "use_cache": true,
+  "vocab_size": 130560
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "temperature": 0.9,
+  "top_p": 0.95,
+  "transformers_version": "5.6.2"
+}
--- a/image.jpg
+++ b/image.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525684ae1cde34d5817f3b8bf3a92e5f8b4ba952725dd2d910fb50e1da06c1c0
+size 407900
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549fabc06393e1b6dd4dc8a8b19dffe3ca95aee429eedd1d15aaac3d56d72d55
+size 2161290944
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}