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

[NPU] Update deepseek support in python examples and quickstart (#12786)

Browse source
This commit is contained in:
binbin Deng 2025-02-07 11:25:16 +08:00 committed by GitHub
parent b4f2be2b09
commit 6ff7faa781
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 11 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/mddocs/Quickstart/npu_quickstart.md
View file

@ -135,6 +135,7 @@ Refer to the following table for examples of verified models:
| Qwen 2 | [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct), [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Meteor Lake, Lunar Lake, Arrow Lake |
| Qwen 2.5 | [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Lunar Lake |
| | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Meteor Lake, Lunar Lake, Arrow Lake |
| DeepSeek-R1 | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B), [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Meteor Lake, Lunar Lake, Arrow Lake |
| MiniCPM | [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16), [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Meteor Lake, Lunar Lake, Arrow Lake |
| Baichuan 2 | [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/) | Lunar Lake |
| MiniCPM-Llama3-V-2_5 | [openbmb/MiniCPM-Llama3-V-2_5](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/Multimodal/) | Lunar Lake |
@ -164,6 +165,7 @@ Refer to the following table for examples of verified models:
| Qwen 2 | [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct), [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples) | Meteor Lake, Lunar Lake, Arrow Lake |
| Qwen 2.5 | [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples) | Lunar Lake |
| | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples) | Meteor Lake, Lunar Lake, Arrow Lake |
| DeepSeek-R1 | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B), [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples) | Meteor Lake, Lunar Lake, Arrow Lake |
| MiniCPM | [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16), [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) | [link](../../../python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples) | Meteor Lake, Lunar Lake, Arrow Lake |
> [!TIP]

9
python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
View file

@ -11,6 +11,7 @@ In this directory, you will find examples on how to directly run HuggingFace `tr
| GLM-Edge | [THUDM/glm-edge-1.5b-chat](https://huggingface.co/THUDM/glm-edge-1.5b-chat), [THUDM/glm-edge-4b-chat](https://huggingface.co/THUDM/glm-edge-4b-chat) |
| Qwen2 | [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct), [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) |
| Qwen2.5 | [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) |
| DeepSeek-R1 | [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B), [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) |
| MiniCPM | [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16), [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) |
| Baichuan2 | [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat) |
@ -53,6 +54,8 @@ The examples below show how to run the **_optimized HuggingFace model implementa
- [Qwen2-7B](./qwen.py)
- [Qwen2.5-3B](./qwen.py)
- [Qwen2.5-7B](./qwen.py)
- [DeepSeek-R1-Distill-Qwen-1.5B](./qwen.py)
- [DeepSeek-R1-Distill-Qwen-7B](./qwen.py)
- [MiniCPM-1B](./minicpm.py)
- [MiniCPM-2B](./minicpm.py)
- [Baichuan2-7B](./baichuan2.py)
@ -89,6 +92,12 @@ python qwen.py --repo-id-or-model-path "Qwen/Qwen2.5-3B-Instruct" --low-bit asym
:: to run Qwen2.5-7B-Instruct
python qwen.py --repo-id-or-model-path "Qwen/Qwen2.5-7B-Instruct" --save-directory <converted_model_path>
:: to run DeepSeek-R1-Distill-Qwen-1.5B
python qwen.py --repo-id-or-model-path "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B" --save-directory <converted_model_path>
:: to run DeepSeek-R1-Distill-Qwen-7B
python qwen.py --repo-id-or-model-path "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" --save-directory <converted_model_path>
:: to run MiniCPM-1B-sft-bf16
python minicpm.py --repo-id-or-model-path "openbmb/MiniCPM-1B-sft-bf16" --save-directory <converted_model_path>