Upload folder using huggingface_hub

.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

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1737971823

README.md

@@ -1,3 +1,50 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# DeepSeek-R1-1.5B-Qwen-MNN
+
+## Introduction
+This model is a 4-bit quantized version of the MNN model exported from [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) 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/DeepSeek-R1-1.5B-Qwen-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/DeepSeek-R1-1.5B-Qwen-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/DeepSeek-R1-1.5B-Qwen-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/DeepSeek-R1-1.5B-Qwen-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)

config.json

@@ -0,0 +1,9 @@
+{
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "low",
+    "memory": "low",
+    "use_template":false
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"other","task":"text-generation"}

embeddings_bf16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceae2992cd5aa74dd18a9bed0313da6db56b4c6c47e804fd1181bb6afb1d6668
+size 466747392

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b38872598164ce3c19a7645e30f4f0fd58203f545f7e07d04206db7254d41ac
+size 1145128

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f15e03a173d99606df1467a9bf5d4e87658e0a715a650dac5f97f5a9da999fd
+size 1081651682

llm_config.json

@@ -0,0 +1,14 @@
+{
+    "hidden_size": 1536,
+    "layer_nums": 28,
+    "attention_mask": "float",
+    "key_value_shape": [
+        2,
+        1,
+        0,
+        2,
+        128
+    ],
+    "prompt_template": "\n<|im_start|>user\n%s<|im_end|>\n<|im_start|>assistant\n",
+    "is_visual": false
+}