|
--- |
|
library_name: transformers |
|
license: bsd-3-clause |
|
base_model: |
|
- Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4 |
|
tags: |
|
- Qwen |
|
- Qwen2.5-1.5B-Instruct |
|
- Qwen2.5-1.5B-Instruct-GPTQ-Int4 |
|
- GPTQ |
|
- Int4 |
|
--- |
|
|
|
# Qwen2.5-1.5B-Instruct-GPTQ-Int4 |
|
|
|
This version of Qwen2.5-1.5B-Instruct-GPTQ-Int4 has been converted to run on the Axera NPU using **w4a16** quantization. |
|
|
|
This model has been optimized with the following LoRA: |
|
|
|
Compatible with Pulsar2 version: 3.4(Not released yet) |
|
|
|
## Convert tools links: |
|
|
|
For those who are interested in model conversion, you can try to export axmodel through the original repo : https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4 |
|
|
|
[Pulsar2 Link, How to Convert LLM from Huggingface to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/appendix/build_llm.html) |
|
|
|
[AXera NPU LLM Runtime](https://github.com/AXERA-TECH/ax-llm) |
|
|
|
## Support Platform |
|
|
|
- AX650 |
|
- AX650N DEMO Board |
|
- [M4N-Dock(η±θ―ζ΄ΎPro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html) |
|
- [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html) |
|
- AX630C |
|
- *developing* |
|
|
|
|Chips|w8a16|w4a16| |
|
|--|--|--| |
|
|AX650| 11 tokens/sec|19 tokens/sec| |
|
|
|
## How to use |
|
|
|
Download all files from this repository to the device |
|
|
|
``` |
|
root@ax650:/mnt/qtang/llm-test/qwen2.5-1.5b# tree -L 1 |
|
. |
|
βββ qwen2.5-1.5b-gptq-int4-ax650 |
|
βββ qwen2.5_tokenizer |
|
βββ qwen2.5_tokenizer.py |
|
βββ main_axcl_aarch64 |
|
βββ main_axcl_x86 |
|
βββ main_prefill |
|
βββ post_config.json |
|
βββ run_qwen2.5_1.5b_gptq_int4_ax650.sh |
|
βββ run_qwen2.5_1.5b_gptq_int4_axcl_aarch64.sh |
|
βββ run_qwen2.5_1.5b_gptq_int4_axcl_x86.sh |
|
``` |
|
|
|
#### Start the Tokenizer service |
|
|
|
``` |
|
root@ax650:/mnt/qtang/llm-test/qwen2.5-1.5b# python3 qwen2.5_tokenizer.py --port 12345 |
|
None None 151645 <|im_end|> |
|
<|im_start|>system |
|
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|> |
|
<|im_start|>user |
|
hello world<|im_end|> |
|
<|im_start|>assistant |
|
|
|
[151644, 8948, 198, 2610, 525, 1207, 16948, 11, 3465, 553, 54364, 14817, 13, 1446, 525, 264, 10950, 17847, 13, 151645, 198, 151644, 872, 198, 14990, 1879, 151645, 198, 151644, 77091, 198] |
|
http://localhost:12345 |
|
``` |
|
|
|
#### Inference with AX650 Host, such as M4N-Dock(η±θ―ζ΄ΎPro) or AX650N DEMO Board |
|
|
|
Open another terminal and run `run_qwen2.5_1.5b_gptq_int4_ax650.sh` |
|
|
|
``` |
|
root@ax650:/mnt/qtang/llm-test/qwen2.5-1.5b# ./run_qwen2.5_1.5b_gptq_int4_ax650.sh |
|
[I][ Init][ 125]: LLM init start |
|
bos_id: -1, eos_id: 151645 |
|
100% | ββββββββββββββββββββββββββββββββ | 31 / 31 [1.62s<1.62s, 19.14 count/s] init post axmodel ok,remain_cmm(2731 MB) |
|
[I][ Init][ 241]: max_token_len : 1023 |
|
[I][ Init][ 246]: kv_cache_size : 256, kv_cache_num: 1023 |
|
[I][ Init][ 254]: prefill_token_num : 128 |
|
[I][ load_config][ 281]: load config: |
|
{ |
|
"enable_repetition_penalty": false, |
|
"enable_temperature": true, |
|
"enable_top_k_sampling": true, |
|
"enable_top_p_sampling": false, |
|
"penalty_window": 20, |
|
"repetition_penalty": 1.2, |
|
"temperature": 0.9, |
|
"top_k": 10, |
|
"top_p": 0.8 |
|
} |
|
|
|
[I][ Init][ 268]: LLM init ok |
|
Type "q" to exit, Ctrl+c to stop current running |
|
>> who are you |
|
I am Qwen, a large language model created by Alibaba Cloud. I assist people with language translation and o ther tasks by understanding human language and generating more appropriate words, phrases, or sentences. |
|
|
|
[N][ Run][ 610]: hit eos,avg 18.68 token/s |
|
|
|
>> 1+1=? |
|
1+1 equals 2. |
|
|
|
[N][ Run][ 610]: hit eos,avg 19.43 token/s |
|
``` |
|
|
|
#### Inference with M.2 Accelerator card |
|
|
|
[What is M.2 Accelerator card?](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html), Show this DEMO based on Raspberry PI 5. |
|
|
|
``` |
|
(base) axera@raspberrypi:~/samples/qwen2.5-1.5b $ ./run_qwen2.5_1.5b_gptq_int4_axcl_aarch64.sh |
|
build time: Feb 13 2025 15:44:57 |
|
[I][ Init][ 111]: LLM init start |
|
bos_id: -1, eos_id: 151645 |
|
100% | ββββββββββββββββββββββββββββββββ | 31 / 31 [22.80s<22.80s, 1.36 count/s] init post axmodel okremain_cmm(6219 MB) |
|
[I][ Init][ 226]: max_token_len : 1023 |
|
[I][ Init][ 231]: kv_cache_size : 256, kv_cache_num: 1023 |
|
[I][ load_config][ 282]: load config: |
|
{ |
|
"enable_repetition_penalty": false, |
|
"enable_temperature": true, |
|
"enable_top_k_sampling": true, |
|
"enable_top_p_sampling": false, |
|
"penalty_window": 20, |
|
"repetition_penalty": 1.2, |
|
"temperature": 0.9, |
|
"top_k": 10, |
|
"top_p": 0.8 |
|
} |
|
|
|
[I][ Init][ 288]: LLM init ok |
|
Type "q" to exit, Ctrl+c to stop current running |
|
|
|
>> who are you |
|
I am Qwen, an AI developed by Alibaba Cloud. I can help you find resources, answer questions, express myself, and interact with you in multiple ways such as text, speech, and image. Please feel free to let me know how I can assist you. |
|
|
|
[N][ Run][ 610]: hit eos,avg 15.36 token/s |
|
|
|
>> q |
|
|
|
(base) axera@raspberrypi:~/samples/qwen2.5-1.5b $ axcl-smi |
|
+------------------------------------------------------------------------------------------------+ |
|
| AXCL-SMI V2.26.0_20250205130139 Driver V2.26.0_20250205130139 | |
|
+-----------------------------------------+--------------+---------------------------------------+ |
|
| Card Name Firmware | Bus-Id | Memory-Usage | |
|
| Fan Temp Pwr:Usage/Cap | CPU NPU | CMM-Usage | |
|
|=========================================+==============+=======================================| |
|
| 0 AX650N V2.26.0 | 0000:01:00.0 | 170 MiB / 945 MiB | |
|
| -- 39C -- / -- | 0% 0% | 1053 MiB / 7040 MiB | |
|
+-----------------------------------------+--------------+---------------------------------------+ |
|
|
|
+------------------------------------------------------------------------------------------------+ |
|
| Processes: | |
|
| Card PID Process Name NPU Memory Usage | |
|
|================================================================================================| |
|
| 0 17325 /home/axera/samples/qwen2.5-1.5b/main_axcl_aarch64 1037736 KiB | |
|
+------------------------------------------------------------------------------------------------+ |
|
``` |
|
|
