Add support for Baichuan2

Below is an example for baichuan-inc/Baichuan2-7B-Chat:
python3 run_generation.py \
--model_name_or_path baichuan-inc/Baichuan2-7B-Chat \
--bf16 --trim_logits --batch_size 1 \
--max_input_tokens 1024 --max_new_tokens 512 \
--use_kv_cache --use_hpu_graphs --use_flash_attention \
--reuse_cache \
--no-ignore_eos

Below is an example for baichuan-inc/Baichuan2-13B-Chat:
python3 run_generation.py \
--model_name_or_path baichuan-inc/Baichuan2-13B-Chat \
--bf16 --trim_logits --batch_size 1 \
--max_input_tokens 1024 --max_new_tokens 512 \
--use_kv_cache --use_hpu_graphs --bucket_size 256 \
--bucket_internal --reuse_cache \
--no-ignore_eos

Co-authored-by: Jianqian Zhou <[email protected]>
Co-authored-by: Wei Lin <[email protected]>
Signed-off-by: Haihao Xiang <[email protected]>

Author: 3 people

README.md

@@ -239,6 +239,7 @@ The following model architectures, tasks and device distributions have been vali
 | DETR |   | <div style="text-align:left"><li>Single card</li></div> | <li>[object detection](https://github.com/huggingface/optimum-habana/tree/main/examples/object-detection)</li> |
 | Mllama     | <div style="text-align:left"><li>LoRA</li></div> | :heavy_check_mark: | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
 | MiniCPM3 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
+| Baichuan2 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 
 </div>
 

docs/source/index.mdx

@@ -106,6 +106,7 @@ In the tables below, ✅ means single-card, multi-card and DeepSpeed have all be
 | DETR         |          | <div style="text-align:left"><li>Single card</li></div> | <li>[object detection](https://github.com/huggingface/optimum-habana/tree/main/examples/object-detection)</li> |
 | Mllama     | <div style="text-align:left"><li>LoRA</li></div> |✅      | <li>[image to text](https://github.com/huggingface/optimum-habana/tree/main/examples/image-to-text)</li> |
 | MiniCPM3 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
+| Baichuan2 |   | <div style="text-align:left"><li>Single card</li></div> | <li>[text generation](https://github.com/huggingface/optimum-habana/tree/main/examples/text-generation)</li> |
 
 - Diffusers