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

Update README.md (#11964)

Browse source
This commit is contained in:
Jason Dai 2024-08-29 18:56:35 +08:00 committed by GitHub
parent 14b2c8dc32
commit 431affd0a0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
View file

@ -1,5 +1,5 @@
# Run Large Language Model on Intel NPU
In this directory, you will find examples on how you could apply IPEX-LLM INT4 or INT8 optimizations on LLM models on [Intel NPUs](../../../README.md). See the table blow for verified models.
# Run HuggingFace `transformers` Models on Intel NPU
In this directory, you will find examples on how to directly run HuggingFace `transformers` models on Intel NPUs (leveraging *Intel NPU Acceleration Library*). See the table blow for verified models.
## Verified Models
@ -52,7 +52,7 @@ For optimal performance, it is recommended to set several environment variables.
set BIGDL_USE_NPU=1
```
## 3. Run models
## 3. Run Models
In the example [generate.py](./generate.py), we show a basic use case for a Llama2 model to predict the next N tokens using `generate()` API, with IPEX-LLM INT4 optimizations on Intel NPUs.
```
@ -77,7 +77,7 @@ done
```
## 4. Run Optimized Models (Experimental)
The example below shows how to run the **_optimized model implementations_** on Intel NPU, including
The examples below show how to run the **_optimized HuggingFace model implementations_** on Intel NPU, including
- [Llama2-7B](./llama.py)
- [Llama3-8B](./llama.py)
- [Qwen2-1.5B](./qwen2.py)
@ -92,7 +92,7 @@ Supported models: Llama2-7B, Qwen2-1.5B, Qwen2-7B, MiniCPM-1B, Baichuan2-7B
#### 32.0.101.2715
Supported models: Llama3-8B, MiniCPM-2B
### Run Models
### Run
```bash
# to run Llama-2-7b-chat-hf
python llama.py