Upload folder using huggingface_hub
Browse files- README.md +38 -1
- config.json +3 -4
- llm.mnn +3 -0
- llm.mnn.json +3 -0
- llm.mnn.weight +3 -0
- llm_config.json +1 -2
README.md
CHANGED
@@ -9,5 +9,42 @@ tags:
|
|
9 |
# Yi-6B-Chat-MNN
|
10 |
|
11 |
## Introduction
|
|
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
# Yi-6B-Chat-MNN
|
10 |
|
11 |
## Introduction
|
12 |
+
This model is a 4-bit quantized version of the MNN model exported from [Yi-6B-Chat](https://modelscope.cn/models/01ai/Yi-6B-Chat/summary) using [llmexport](https://github.com/alibaba/MNN/tree/master/transformers/llm/export).
|
13 |
|
14 |
+
## Download
|
15 |
+
```bash
|
16 |
+
# install huggingface
|
17 |
+
pip install huggingface
|
18 |
+
```
|
19 |
+
```bash
|
20 |
+
# shell download
|
21 |
+
huggingface download --model 'taobao-mnn/Yi-6B-Chat-MNN' --local_dir 'path/to/dir'
|
22 |
+
```
|
23 |
+
```python
|
24 |
+
# SDK download
|
25 |
+
from huggingface_hub import snapshot_download
|
26 |
+
model_dir = snapshot_download('taobao-mnn/Yi-6B-Chat-MNN')
|
27 |
+
```
|
28 |
+
|
29 |
+
```bash
|
30 |
+
# git clone
|
31 |
+
git clone https://www.modelscope.cn/taobao-mnn/Yi-6B-Chat-MNN
|
32 |
+
```
|
33 |
+
|
34 |
+
## Usage
|
35 |
+
```bash
|
36 |
+
# clone MNN source
|
37 |
+
git clone https://github.com/alibaba/MNN.git
|
38 |
+
|
39 |
+
# compile
|
40 |
+
cd MNN
|
41 |
+
mkdir build && cd build
|
42 |
+
cmake .. -DMNN_LOW_MEMORY=true -DMNN_CPU_WEIGHT_DEQUANT_GEMM=true -DMNN_BUILD_LLM=true -DMNN_SUPPORT_TRANSFORMER_FUSE=true
|
43 |
+
make -j
|
44 |
+
|
45 |
+
# run
|
46 |
+
./llm_demo /path/to/Yi-6B-Chat-MNN/config.json prompt.txt
|
47 |
+
```
|
48 |
+
|
49 |
+
## Document
|
50 |
+
[MNN-LLM](https://mnn-docs.readthedocs.io/en/latest/transformers/llm.html#)
|
config.json
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
{
|
2 |
-
"llm_model": "
|
3 |
-
"llm_weight": "
|
4 |
-
|
5 |
"backend_type": "cpu",
|
6 |
"thread_num": 4,
|
7 |
"precision": "low",
|
8 |
"memory": "low"
|
9 |
-
}
|
|
|
1 |
{
|
2 |
+
"llm_model": "llm.mnn",
|
3 |
+
"llm_weight": "llm.mnn.weight",
|
|
|
4 |
"backend_type": "cpu",
|
5 |
"thread_num": 4,
|
6 |
"precision": "low",
|
7 |
"memory": "low"
|
8 |
+
}
|
llm.mnn
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c4e9b4b6d0a7c80c54de96b57afa9ba09e7e3b06e483bd33352d13bcbc342b
|
3 |
+
size 2637408
|
llm.mnn.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50ade3ec36f8a4454258acf64673863a960a2562a95ba7e79aa886efe00b4fc9
|
3 |
+
size 16701691
|
llm.mnn.weight
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57245541501bf1f06f5c7c86f35d5416dfae0fe1d8a8169da0748e8b15e95ba5
|
3 |
+
size 3261731670
|
llm_config.json
CHANGED
@@ -10,6 +10,5 @@
|
|
10 |
128
|
11 |
],
|
12 |
"prompt_template": "<|im_start|> user\n%s<|im_end|>\n<|im_start|> assistant\n",
|
13 |
-
"is_visual": false
|
14 |
-
"is_single": true
|
15 |
}
|
|
|
10 |
128
|
11 |
],
|
12 |
"prompt_template": "<|im_start|> user\n%s<|im_end|>\n<|im_start|> assistant\n",
|
13 |
+
"is_visual": false
|
|
|
14 |
}
|