ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

update doc about gemma random and unreadable output. (#10297)

Browse source 
* Update install_gpu.md

* Update README.md

* Update README.md
This commit is contained in:
Xin Qiu 2024-03-01 15:41:16 +08:00 committed by GitHub
parent beb9433cec
commit 509e206de0
2 changed files with 23 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
docs/readthedocs/source/doc/LLM/Overview/install_gpu.md
View file

@ -530,6 +530,15 @@ The following packages have unmet dependencies:
You can use `sudo apt install -y intel-i915-dkms intel-fw-gpu` to install instead. As the intel-platform-cse-dkms and intel-platform-vsec-dkms are already provided by intel-i915-dkms.
### 3. Gemma-7b-it's output is random and unreadable on Arc770 ubuntu 22.04.
The output of `What's AI?` like:
```
wiedzy Artificial Intelligence meliti: Artificial Intelligence undenti beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng
```
Please check your driver version and OneAPI version. Commnad is `sudo apt list --installed | egrep "intel-basekit|intel-level-zero-gpu"`.
Make sure intel-basekit>=2024.0.1-43 and intel-level-zero-gpu>=1.3.27191.42-775~22.04.
### Troubleshooting
#### 1. Cannot open shared object file: No such file or directory

17
python/llm/example/GPU/HF-Transformers-AutoModels/Model/gemma/README.md
View file

@ -116,8 +116,8 @@ In the example, several arguments can be passed to satisfy your requirements:
- `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is AI?'`.
- `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
#### 2.3 Sample Output
#### [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
##### Sample Output
##### [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it)
```log
Inference time: xxxx s
-------------------- Output --------------------
@ -127,7 +127,7 @@ model
**Artificial Intelligence (AI)** is a field of computer science that involves the creation of intelligent machines capable of performing tasks typically requiring human intelligence, such as learning,
```
#### [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it)
##### [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it)
```log
Inference time: xxxx s
-------------------- Output --------------------
@ -136,3 +136,14 @@ What is AI?
model
**Artificial intelligence (AI)** is the simulation of human cognitive functions, such as learning, reasoning, and problem-solving, by machines. AI systems are designed
```
### 5. Know issue
Gemma-7b-it's output is random and unreadable on Arc770 ubuntu 22.04.
The output of `What's AI?` like:
```
wiedzy Artificial Intelligence meliti: Artificial Intelligence undenti beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng
```
Please check your driver version and OneAPI version. Commnad is `sudo apt list --installed | egrep "intel-basekit|intel-level-zero-gpu"`.
Make sure intel-basekit>=2024.0.1-43 and intel-level-zero-gpu>=1.3.27191.42-775~22.04.