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 +1,50 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# Qwen2.5-VL-3B-Instruct-MNN
+
+## Introduction
+This model is a 4-bit quantized version of the MNN model exported from Qwen2.5-VL-3B-Instruct 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/Qwen2.5-VL-3B-Instruct-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/Qwen2.5-VL-3B-Instruct-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/Qwen2.5-VL-3B-Instruct-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/Qwen2.5-VL-3B-Instruct-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)

config.json

@@ -0,0 +1,14 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "mllm": {
+        "backend_type": "cpu",
+        "thread_num": 4,
+        "precision": "low",
+        "memory": "low"
+    }
+}

embeddings_bf16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84907567aa829c6f24cadbdeb68c3c44d25fc0a8be8e917fd603cb64f72810d
+size 622329856

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad73eb6e069ff4ca3f6262d9bcf90e9ba59d7e84438f8863386b5d60df6f36c
+size 1810160

llm.mnn.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bf49d854e4046dd0a05a9bc9c1fe453430bb84d034ad17f237556b7f205bd0
+size 10567306

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df69926fe13d47dc075c5559f1455f734b26c144962a5a85ca8637f079156e8
+size 1736078786

llm_config.json

@@ -0,0 +1,28 @@
+{
+    "hidden_size": 2048,
+    "layer_nums": 36,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        2,
+        128
+    ],
+    "prompt_template": "<|im_start|>user\n%s<|im_end|>\n<|im_start|>assistant\n",
+    "is_visual": true,
+    "image_mean": [
+        122.7709383,
+        116.7460125,
+        104.09373615000001
+    ],
+    "image_norm": [
+        0.01459842661924292,
+        0.015007768493717056,
+        0.014220065717024088
+    ],
+    "image_size": 420,
+    "vision_start": 151652,
+    "vision_end": 151653,
+    "image_pad": 151655
+}

visual.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b93a8460b5fd1a2128945fa3ffe4c582141866366e23fc9bcb2338ecedc9ab
+size 717328

visual.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ec4c8034c734a8928edf1843b6212d99b4e2c1fdd1ea3f71d346fb06718b99
+size 369748896