Update README.md
Browse files
README.md
CHANGED
|
@@ -33,9 +33,11 @@ There is an open clash in dependencies versions between optiumum-intel and openv
|
|
| 33 |
|
| 34 |
|
| 35 |
So for the model conversion the only dependency you need is
|
| 36 |
-
|
|
|
|
| 37 |
```
|
| 38 |
-
pip install
|
|
|
|
| 39 |
```
|
| 40 |
This command will install, among others:
|
| 41 |
```
|
|
@@ -54,6 +56,8 @@ After the previous step you are enabled to run the following command (considerin
|
|
| 54 |
```bash
|
| 55 |
optimum-cli export openvino --model NuExtract-1.5-tiny --task text-generation-with-past --trust-remote-code --weight-format int8 ov_NuExtract-1.5-tiny
|
| 56 |
```
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
#### Dependencies required to run the model with `openvino-genai`
|
|
|
|
| 33 |
|
| 34 |
|
| 35 |
So for the model conversion the only dependency you need is
|
| 36 |
+
|
| 37 |
+
|
| 38 |
```
|
| 39 |
+
pip install -U "openvino>=2024.3.0" "openvino-genai"
|
| 40 |
+
pip install "torch>=2.1" "nncf>=2.7" "transformers>=4.40.0" "onnx<1.16.2" "optimum>=1.16.1" "accelerate" "datasets>=2.14.6" "git+https://github.com/huggingface/optimum-intel.git" --extra-index-url https://download.pytorch.org/whl/cpu
|
| 41 |
```
|
| 42 |
This command will install, among others:
|
| 43 |
```
|
|
|
|
| 56 |
```bash
|
| 57 |
optimum-cli export openvino --model NuExtract-1.5-tiny --task text-generation-with-past --trust-remote-code --weight-format int8 ov_NuExtract-1.5-tiny
|
| 58 |
```
|
| 59 |
+
this will start the process and produce the following messages, without any fatal error
|
| 60 |
+
|
| 61 |
|
| 62 |
|
| 63 |
#### Dependencies required to run the model with `openvino-genai`
|