Upload folder using huggingface_hub

README.md

@@ -9,5 +9,42 @@ tags:
 # internlm-chat-7b-MNN
 
 ## Introduction
+This model is a 4-bit quantized version of the MNN model exported from [internlm-chat-7b](https://modelscope.cn/models/AI-ModelScope/internlm-chat-7b/summary) using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export).
 
-This model is a 4-bit quantized version of the MNN model exported from internlm-chat-7b using [llm-export](https://github.com/wangzhaode/llm-export).
+## Download
+```bash
+# install huggingface
+pip install huggingface
+```
+```bash
+# shell download
+huggingface download --model 'taobao-mnn/internlm-chat-7b-MNN' --local_dir 'path/to/dir'
+```
+```python
+# SDK download
+from huggingface_hub import snapshot_download
+model_dir = snapshot_download('taobao-mnn/internlm-chat-7b-MNN')
+```
+
+```bash
+# git clone
+git clone https://www.modelscope.cn/taobao-mnn/internlm-chat-7b-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/internlm-chat-7b-MNN/config.json prompt.txt
+```
+
+## Document
+[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)

config.json

@@ -1,7 +1,6 @@
 {
-    "llm_model": "internlm-7b-int4.mnn",
-    "llm_weight": "internlm-7b-int4.mnn.weight",
-
+    "llm_model": "llm.mnn",
+    "llm_weight": "llm.mnn.weight",
     "backend_type": "cpu",
     "thread_num": 4,
     "precision": "low",

llm.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04939de119ab73f1295b708dde7f47a568ef3ecc9c6ff0c539e3188284b05140
+size 2636368

llm.mnn.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc9c60b3eec482728782c86931bf8e15a65d2299be0cbb00a1304973284bf2c
+size 16728576

llm.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c33b10e8e8e4604b6a933d3f7cee3da6c9f3288483ea018ce511c4be43faea6
+size 3882554202

llm_config.json

@@ -10,6 +10,5 @@
         128
     ],
     "prompt_template": "<|User|>:%s<eoh>\n<|Bot|>:",
-    "is_visual": false,
-    "is_single": true
+    "is_visual": false
 }

tokenizer.txt

@@ -1,6 +1,6 @@
 430 0
-3 2 1
-0 1 2 2 2 1
+3 1 1
+0 1 2 2 1 
 103168
 PHVuaz4= 0.0 2
 PHM+ 0.0 3