Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,38 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.mnn filter=lfs diff=lfs merge=lfs -text
+*.mnn.* filter=lfs diff=lfs merge=lfs -text
+*.weight filter=lfs diff=lfs merge=lfs -text
+    

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# gemma-3-270m-it-MNN
+
+## Introduction
+This model is a 4-bit quantized version of the MNN model exported from gemma-3-270m-it using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export).
+
+## Download
+```bash
+# install huggingface
+pip install huggingface
+```
+```bash
+# shell download
+huggingface download --model 'taobao-mnn/gemma-3-270m-it-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/gemma-3-270m-it-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/gemma-3-270m-it-MNN
+```
+
+## Usage
+```bash
+# clone MNN source
+git clone https://github.com/alibaba/MNN.git
+
+# compile
+cd MNN
+mkdir build && cd build
+cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true
+make -j
+
+# run
+./llm_demo /path/to/gemma-3-270m-it-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
+    

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
+}

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584b72890da15f85f5aedc81d7a202ef7b402c8e78f032031a382dc2c4a55190
+size 347904

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805d281786a42c4c1ab8d79709ca8614c4e9fdd6145af9fabebea9ad30021638
+size 302028286

llm_config.json

@@ -0,0 +1,31 @@
+{
+    "hidden_size": 640,
+    "layer_nums": 18,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        1,
+        256
+    ],
+    "bos": "<bos><start_of_turn>user\n",
+    "system_prompt_template": "%s\n\n",
+    "user_prompt_template": "%s<end_of_turn>\n",
+    "assistant_prompt_template": "<start_of_turn>model\n%s<end_of_turn>\n<start_of_turn>user\n",
+    "is_visual": false,
+    "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": [
+        113284606,
+        281056766,
+        20971520,
+        8,
+        64
+    ]
+}