初始化项目，由ModelHub XC社区提供模型

Model: MuXodious/Gemma3NPC-1b-SOMPOA-heresy
Source: Original Platform

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,166 @@
+---
+base_model:
+- chimbiwide/Gemma3NPC-1b
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- gemma3_text
+- heretic
+- uncensored
+- decensored
+- abliterated
+license: gemma
+language:
+- en
+---
+
+This is a **Gemma3NPC-1b** fine-tune, produced at the request of [redaihf](https://huggingface.co/redaihf) through P-E-W's [Heretic](https://github.com/p-e-w/heretic) (v1.2.0) abliteration engine with [Self-Organizing Maps & Magnitude-Preserving Orthogonal Ablation](https://github.com/p-e-w/heretic/pull/196) enabled.
+
+**Note:** Model remains untested.
+
+---
+<img src="https://img.shields.io/badge/RENEGADE_CHAPTER-SOMPOA-FCC900?style=flat-square&labelColor=101010" align="right" width="300">
+
+**Heretication Results**
+
+| Score Metric | Value | Parameter | Value |
+| :--- | :--- | :--- | :--- |
+| **Refusals** | 15/416 | **direction_index** | per layer |
+| **KL Divergence** | 0.0571  | **attn.o_proj.max_weights.0** | 0: 1.01 |
+| **Initial Refusals** | 378/416 | **attn.o_proj.max_weights.1** | 1: 0.82 |
+||| **attn.o_proj.max_weights.2** | 2: 0.81 |
+||| **attn.o_proj.max_weights.3** | 3: 1.48 |
+||| **attn.o_proj.max_weight_position** | 17.02 |
+||| **attn.o_proj.min_weights.0** | 0: 0.94 |
+||| **attn.o_proj.min_weights.1** | 1: 0.34 |
+||| **attn.o_proj.min_weights.2** | 2: 0.38 |
+||| **attn.o_proj.min_weights.3** | 3: 0.07 |
+||| **attn.o_proj.min_weight_distance** | 10.47 |
+||| **mlp.down_proj.max_weights.0** | 0: 1.10 |
+||| **mlp.down_proj.max_weights.1** | 1: 1.18 |
+||| **mlp.down_proj.max_weights.2** | 2: 1.32 |
+||| **mlp.down_proj.max_weights.3** | 3: 1.34 |
+||| **mlp.down_proj.max_weight_position** | 20.96 |
+||| **mlp.down_proj.min_weights.0** | 0: 0.12 |
+||| **mlp.down_proj.min_weights.1** | 1: 0.73 |
+||| **mlp.down_proj.min_weights.2** | 2: 0.54 |
+||| **mlp.down_proj.min_weights.3** | 3: 0.84 |
+||| **mlp.down_proj.min_weight_distance** | 5.03 |
+
+---
+**Appendix**
+
+> Empty system prompt.
+
+<details>
+  <summary>Heretication Rituals</summary>
+  
+```
+   [Trial 148] Refusals:  9/416, KL divergence: 0.0792
+   [Trial 265] Refusals: 10/416, KL divergence: 0.0657
+ » [Trial 306] Refusals: 15/416, KL divergence: 0.0571
+   [Trial 375] Refusals: 24/416, KL divergence: 0.0551
+   [Trial 351] Refusals: 25/416, KL divergence: 0.0494
+   [Trial 350] Refusals: 28/416, KL divergence: 0.0490
+   [Trial 250] Refusals: 35/416, KL divergence: 0.0424
+   [Trial 346] Refusals: 40/416, KL divergence: 0.0386
+   [Trial 358] Refusals: 52/416, KL divergence: 0.0370
+   [Trial 240] Refusals: 55/416, KL divergence: 0.0361
+   [Trial 226] Refusals: 57/416, KL divergence: 0.0361
+   [Trial 383] Refusals: 75/416, KL divergence: 0.0289
+   [Trial 377] Refusals: 97/416, KL divergence: 0.0281
+   [Trial 286] Refusals: 121/416, KL divergence: 0.0276
+```
+
+</details>
+
+<details>
+  <summary>PIQA Benchmarks</summary>
+
+```
+┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳
+┃ Benchmark ┃ Metric               ┃  Value  ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━┩
+│ PIQA Base │ acc,none             │  0.7291 │
+│           │ acc_stderr,none      │  0.0104 │
+│           │ acc_norm,none        │  0.7301 │
+│           │ acc_norm_stderr,none │  0.0104 │
+└───────────┴──────────────────────┴─────────┴
+┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┓
+┃ Benchmark ┃ Metric               ┃  Value ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━┩
+│ PIQA T265 │ acc,none             │ 0.7296 │
+│           │ acc_stderr,none      │ 0.0104 │
+│           │ acc_norm,none        │ 0.7323 │
+│           │ acc_norm_stderr,none │ 0.0103 │
+└───────────┴──────────────────────┴────────┘
+┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┓
+┃ Benchmark ┃ Metric               ┃  Value ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━┩
+│ PIQA T148 │ acc,none             │ 0.7291 │
+│           │ acc_stderr,none      │ 0.0104 │
+│           │ acc_norm,none        │ 0.7361 │
+│           │ acc_norm_stderr,none │ 0.0103 │
+└───────────┴──────────────────────┴────────┘
+┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┓
+┃ Benchmark ┃ Metric               ┃  Value ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━┩
+│ PIQA T306 │ acc,none             │ 0.7296 │
+│           │ acc_stderr,none      │ 0.0104 │
+│           │ acc_norm,none        │ 0.7334 │
+│           │ acc_norm_stderr,none │ 0.0103 │
+└───────────┴──────────────────────┴────────┘
+```
+
+</details>
+
+---
+# Gemma3NPC-1b
+
+**A new attempt in training Gemma3NPC.**
+
+***Tensorboard data are available!***
+
+---
+
+It's been a while since the last Gemma3NPC model release, in the mean while we were working on some other models like [GemmaThink](https://huggingface.co/collections/chimbiwide/gemmathink).
+
+Now we are back with the newest **Gemma3NPC-1b**, trained using our [RolePlay-NPCv2](https://huggingface.co/datasets/chimbiwide/RolePlay-NPCv2) dataset.
+
+---
+
+### Training Parameters
+
+We trained this model as a rank-32 LoRA adapter with two epoches over `RolePlay-NPCv2` using a 80GB A100 in Google Colab. For this run, we employed a learning rate of `2e-5` and a total batch size of 8 and gradient accumulation steps of 4. A cosine learning rate scheduler was used with an 150-step warmup. With a gradient clipping of 1.0.
+
+Check out our training notebook [here](https://github.com/chimbiwide/Gemma3NPC/blob/main/Training/Gemma3NPC_1b.ipynb).
+
+---
+
+### Changes & Performance
+
+With this new 1b model, we used much more aggresive training parameters and added some NSFW dataset to experiment with the results. We noticed a few really interesting responses:
+
+- **There seems to be some sign of "reasoning"**
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/K-RdDLXbkZSNuf-bFZU8P.png)
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/WTPMNS2A8skZ0cwm43YTH.png)
+
+- **The model is less likely to break out of character**
+- 
+  Something up to the users to explore for themselves, remember to provide a roleplaying prompt first!
+
+---
+
+### Future Work
+
+Now, we will be focusing on further improving Gemma3NPC, not only just through training parameters. 
+1. Better data (most of our data are old and need an update), either collected or synthetically generated.
+2. Better & new models, expand beyond Gemma3 model family, our next goal is a Qwen3 based model.
+3. Adding GRPO into the training loop.
+
+These improvements serve our ultimate goal of creating an small agentic NPC model, with good RP quality and tool-calling for dynamic in-game interactions.
+
+We also plan to create some sort of a Unity game demo,it's on its way.

added_tokens.json

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

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 -%}

config.json

@@ -0,0 +1,63 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "initializer_range": 0.02,
+    "intermediate_size": 6912,
+    "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"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": 512,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.2.1",
+    "use_cache": true,
+    "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 106,
+  "pad_token_id": 0,
+  "transformers_version": "5.6.2",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b35e6373bb1bbaefac8681a09e1c4cf13eb136fe5060bdecfaa5a24fbdd17a
+size 1999811208

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": "<end_of_turn>",
+    "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