Add MNN 4-bit quantized model with Model Card

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+llm.mnn filter=lfs diff=lfs merge=lfs -text
+llm.mnn.weight filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+language:
+- en
+license: other
+tags:
+- mnn
+- on-device
+- android
+- ios
+- quantization
+- int4
+- text-generation
+- gemma
+pipeline_tag: text-generation
+library_name: mnn
+base_model: WhoIsShe/gemma-3-1b-it-heretic-extreme-uncensored-abliterated
+---
+
+# Gemma-3-1B (MNN Quantized)
+
+This is a **4-bit quantized** version of the Gemma-3-1B model, optimized for **on-device inference** (Android/iOS) using the [Alibaba MNN framework](https://github.com/alibaba/MNN).
+
+## 🚀 Fast Deployment on Android
+
+### 1. Download the App
+Don't build from scratch! Use the official MNN Chat Android app:
+* **[Download APK (GitHub)](https://github.com/alibaba/MNN/releases)**
+
+### 2. Setup
+1. Download the files from this repo (`llm.mnn`, `llm.mnn.weight`, `config.json`).
+2. Create a folder on your phone: `/sdcard/MNN/gemma-3-1b`.
+3. Copy the files into that folder.
+4. Open the MNN App and select your folder.
+
+## 💻 Technical Details
+* **Framework:** MNN
+* **Quantization:** 4-bit Asymmetric (Int4)
+* **Model Type:** Gemma-3-1B (Uncensored)

config.json

@@ -0,0 +1,10 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "sampler_type": "penalty",
+    "penalty": 1.1
+}

export_args.json

@@ -0,0 +1,41 @@
+{
+    "path": "/content/models/gemma-3-1b-it-heretic-extreme-uncensored-abliterated",
+    "type": null,
+    "tokenizer_path": "/content/models/gemma-3-1b-it-heretic-extreme-uncensored-abliterated",
+    "eagle_path": null,
+    "lora_path": null,
+    "gptq_path": null,
+    "dst_path": "/kaggle/working/mnn_output",
+    "verbose": true,
+    "test": null,
+    "export": "mnn",
+    "onnx_slim": false,
+    "quant_bit": 4,
+    "quant_block": 64,
+    "visual_quant_bit": null,
+    "visual_quant_block": null,
+    "lm_quant_bit": 4,
+    "lm_quant_block": 64,
+    "mnnconvert": "../../../build/MNNConvert",
+    "ppl": false,
+    "awq": false,
+    "hqq": false,
+    "omni": false,
+    "transformer_fuse": false,
+    "group_conv_native": false,
+    "smooth": false,
+    "sym": false,
+    "visual_sym": false,
+    "seperate_embed": false,
+    "lora_split": false,
+    "calib_data": null,
+    "act_bit": 16,
+    "embed_bit": 16,
+    "act_sym": false,
+    "generate_for_npu": false,
+    "skip_weight": false,
+    "omni_epochs": 20,
+    "omni_lr": 0.005,
+    "omni_wd": 0.0001,
+    "tie_word_embeddings": true
+}

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5c2bdaa7fc2807af6c2f80aab77b2375e3b5d8a21ff5b8e001a77e217b8d9e
+size 538064

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813c1d60a94d90e980fb0a409b87756b5e07cc1c7439032014856ea7f70948ba
+size 625923006

llm_config.json

@@ -0,0 +1,19 @@
+{
+    "model_type": "gemma3_text",
+    "hidden_size": 1152,
+    "attention_mask": "float",
+    "attention_type": "mix",
+    "sliding_window": 512,
+    "jinja": {
+        "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",
+        "bos": "<bos>",
+        "eos": "<eos>"
+    },
+    "tie_embeddings": [
+        437179326,
+        588174270,
+        37748736,
+        4,
+        64
+    ]
+}