Skip to content

Commit 3378738

Browse files
Jintao-HuangJintao-Huang
committed
Merge branch 'main' into release/1.6
2 parents 39ec770 + 01ea477 commit 3378738

File tree

7 files changed

+133
-137
lines changed

7 files changed

+133
-137
lines changed

‎README.md‎

Lines changed: 15 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -208,12 +208,24 @@ app_ui_main(infer_args)
208208
- [cogagent](https://github.com/THUDM/CogVLM) series: cogagent-18b-chat, cogagent-18b-instruct.
209209
- [internlm-xcomposer2](https://github.com/InternLM/InternLM-XComposer) series: internlm-xcomposer2-7b-chat.
210210
- General:
211-
- [qwen](https://github.com/QwenLM/Qwen) series: qwen-1_8b, qwen-1_8b-chat, qwen-1_8b-chat-int4, qwen-1_8b-chat-int8, qwen-7b, qwen-7b-chat, qwen-7b-chat-int4, qwen-7b-chat-int8, qwen-14b, qwen-14b-chat, qwen-14b-chat-int4, qwen-14b-chat-int8, qwen-72b, qwen-72b-chat, qwen-72b-chat-int4, qwen-72b-chat-int8.
212-
- [qwen1.5](https://github.com/QwenLM/Qwen1.5) series: qwen1half-0_5b, qwen1half-0_5b-chat, qwen1half-0_5b-chat-int4, qwen1half-0_5b-chat-int8, qwen1half-1_8b, qwen1half-1_8b-chat, qwen1half-1_8b-chat-int4, qwen1half-1_8b-chat-int8, qwen1half-4b, qwen1half-4b-chat, qwen1half-4b-chat-int4, qwen1half-4b-chat-int8, qwen1half-7b, qwen1half-7b-chat, qwen1half-7b-chat-int4, qwen1half-7b-chat-int8, qwen1half-14b, qwen1half-14b-chat, qwen1half-14b-chat-int4, qwen1half-14b-chat-int8, qwen1half-72b, qwen1half-72b-chat, qwen1half-72b-chat-int4, qwen1half-72b-chat-int8.
211+
- [qwen](https://github.com/QwenLM/Qwen) series:
212+
- qwen-1_8b, qwen-1_8b-chat, qwen-1_8b-chat-int4, qwen-1_8b-chat-int8.
213+
- qwen-7b, qwen-7b-chat, qwen-7b-chat-int4, qwen-7b-chat-int8.
214+
- qwen-14b, qwen-14b-chat, qwen-14b-chat-int4, qwen-14b-chat-int8.
215+
- qwen-72b, qwen-72b-chat, qwen-72b-chat-int4, qwen-72b-chat-int8.
216+
- [qwen1.5](https://github.com/QwenLM/Qwen1.5) series:
217+
- qwen1half-0_5b, qwen1half-0_5b-chat, qwen1half-0_5b-chat-int4, qwen1half-0_5b-chat-int8.
218+
- qwen1half-1_8b, qwen1half-1_8b-chat, qwen1half-1_8b-chat-int4, qwen1half-1_8b-chat-int8.
219+
- qwen1half-4b, qwen1half-4b-chat, qwen1half-4b-chat-int4, qwen1half-4b-chat-int8.
220+
- qwen1half-7b, qwen1half-7b-chat, qwen1half-7b-chat-int4, qwen1half-7b-chat-int8.
221+
- qwen1half-14b, qwen1half-14b-chat, qwen1half-14b-chat-int4, qwen1half-14b-chat-int8.
222+
- qwen1half-72b, qwen1half-72b-chat, qwen1half-72b-chat-int4, qwen1half-72b-chat-int8.
213223
- [chatglm](https://github.com/THUDM/ChatGLM-6B) series: chatglm2-6b, chatglm2-6b-32k, chatglm3-6b-base, chatglm3-6b, chatglm3-6b-32k.
214224
- [llama](https://github.com/facebookresearch/llama) series: llama2-7b, llama2-7b-chat, llama2-13b, llama2-13b-chat, llama2-70b, llama2-70b-chat.
215225
- [yi](https://github.com/01-ai/Yi) series: yi-6b, yi-6b-200k, yi-6b-chat, yi-34b, yi-34b-200k, yi-34b-chat.
216-
- [internlm](https://github.com/InternLM/InternLM) series: internlm-7b, internlm-7b-chat, internlm-7b-chat-8k, internlm-20b, internlm-20b-chat, internlm2-7b-base, internlm2-7b, internlm2-7b-sft-chat, internlm2-7b-chat, internlm2-20b-base, internlm2-20b, internlm2-20b-sft-chat, internlm2-20b-chat.
226+
- [internlm](https://github.com/InternLM/InternLM) series:
227+
- internlm-7b, internlm-7b-chat, internlm-7b-chat-8k, internlm-20b, internlm-20b-chat.
228+
- internlm2-7b-base, internlm2-7b, internlm2-7b-sft-chat, internlm2-7b-chat, internlm2-20b-base, internlm2-20b, internlm2-20b-sft-chat, internlm2-20b-chat.
217229
- [deepseek](https://github.com/deepseek-ai/deepseek-LLM) series: deepseek-7b, deepseek-7b-chat, deepseek-67b, deepseek-67b-chat, deepseek-moe-16b, deepseek-moe-16b-chat.
218230
- [openbuddy](https://github.com/OpenBuddy/OpenBuddy) series: openbuddy-llama2-13b-chat, openbuddy-llama-65b-chat, openbuddy-llama2-70b-chat, openbuddy-mistral-7b-chat, openbuddy-zephyr-7b-chat, openbuddy-deepseek-67b-chat.
219231
- [mistral](https://github.com/mistralai/mistral-src) series: mistral-7b, mistral-7b-instruct, mistral-7b-instruct-v2.

‎README_CN.md‎

Lines changed: 15 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -207,12 +207,24 @@ app_ui_main(infer_args)
207207
- [cogagent](https://github.com/THUDM/CogVLM) 系列: cogagent-18b-chat, cogagent-18b-instruct.
208208
- [internlm-xcomposer2](https://github.com/InternLM/InternLM-XComposer) 系列: internlm-xcomposer2-7b-chat.
209209
- 通用:
210-
- [qwen](https://github.com/QwenLM/Qwen) 系列: qwen-1_8b, qwen-1_8b-chat, qwen-1_8b-chat-int4, qwen-1_8b-chat-int8, qwen-7b, qwen-7b-chat, qwen-7b-chat-int4, qwen-7b-chat-int8, qwen-14b, qwen-14b-chat, qwen-14b-chat-int4, qwen-14b-chat-int8, qwen-72b, qwen-72b-chat, qwen-72b-chat-int4, qwen-72b-chat-int8.
211-
- [qwen1.5](https://github.com/QwenLM/Qwen1.5) series: qwen1half-0_5b, qwen1half-0_5b-chat, qwen1half-0_5b-chat-int4, qwen1half-0_5b-chat-int8, qwen1half-1_8b, qwen1half-1_8b-chat, qwen1half-1_8b-chat-int4, qwen1half-1_8b-chat-int8, qwen1half-4b, qwen1half-4b-chat, qwen1half-4b-chat-int4, qwen1half-4b-chat-int8, qwen1half-7b, qwen1half-7b-chat, qwen1half-7b-chat-int4, qwen1half-7b-chat-int8, qwen1half-14b, qwen1half-14b-chat, qwen1half-14b-chat-int4, qwen1half-14b-chat-int8, qwen1half-72b, qwen1half-72b-chat, qwen1half-72b-chat-int4, qwen1half-72b-chat-int8.
210+
- [qwen](https://github.com/QwenLM/Qwen) 系列:
211+
- qwen-1_8b, qwen-1_8b-chat, qwen-1_8b-chat-int4, qwen-1_8b-chat-int8.
212+
- qwen-7b, qwen-7b-chat, qwen-7b-chat-int4, qwen-7b-chat-int8.
213+
- qwen-14b, qwen-14b-chat, qwen-14b-chat-int4, qwen-14b-chat-int8.
214+
- qwen-72b, qwen-72b-chat, qwen-72b-chat-int4, qwen-72b-chat-int8.
215+
- [qwen1.5](https://github.com/QwenLM/Qwen1.5) 系列:
216+
- qwen1half-0_5b, qwen1half-0_5b-chat, qwen1half-0_5b-chat-int4, qwen1half-0_5b-chat-int8.
217+
- qwen1half-1_8b, qwen1half-1_8b-chat, qwen1half-1_8b-chat-int4, qwen1half-1_8b-chat-int8.
218+
- qwen1half-4b, qwen1half-4b-chat, qwen1half-4b-chat-int4, qwen1half-4b-chat-int8.
219+
- qwen1half-7b, qwen1half-7b-chat, qwen1half-7b-chat-int4, qwen1half-7b-chat-int8.
220+
- qwen1half-14b, qwen1half-14b-chat, qwen1half-14b-chat-int4, qwen1half-14b-chat-int8.
221+
- qwen1half-72b, qwen1half-72b-chat, qwen1half-72b-chat-int4, qwen1half-72b-chat-int8.
212222
- [chatglm](https://github.com/THUDM/ChatGLM-6B) 系列: chatglm2-6b, chatglm2-6b-32k, chatglm3-6b-base, chatglm3-6b, chatglm3-6b-32k.
213223
- [llama](https://github.com/facebookresearch/llama) 系列: llama2-7b, llama2-7b-chat, llama2-13b, llama2-13b-chat, llama2-70b, llama2-70b-chat.
214224
- [yi](https://github.com/01-ai/Yi) 系列: yi-6b, yi-6b-200k, yi-6b-chat, yi-34b, yi-34b-200k, yi-34b-chat.
215-
- [internlm](https://github.com/InternLM/InternLM) 系列: internlm-7b, internlm-7b-chat, internlm-7b-chat-8k, internlm-20b, internlm-20b-chat, internlm2-7b-base, internlm2-7b, internlm2-7b-sft-chat, internlm2-7b-chat, internlm2-20b-base, internlm2-20b, internlm2-20b-sft-chat, internlm2-20b-chat.
225+
- [internlm](https://github.com/InternLM/InternLM) 系列:
226+
- internlm-7b, internlm-7b-chat, internlm-7b-chat-8k, internlm-20b, internlm-20b-chat.
227+
- internlm2-7b-base, internlm2-7b, internlm2-7b-sft-chat, internlm2-7b-chat, internlm2-20b-base, internlm2-20b, internlm2-20b-sft-chat, internlm2-20b-chat.
216228
- [deepseek](https://github.com/deepseek-ai/deepseek-LLM) 系列: deepseek-7b, deepseek-7b-chat, deepseek-67b, deepseek-67b-chat, deepseek-moe-16b, deepseek-moe-16b-chat.
217229
- [openbuddy](https://github.com/OpenBuddy/OpenBuddy) 系列: openbuddy-llama2-13b-chat, openbuddy-llama-65b-chat, openbuddy-llama2-70b-chat, openbuddy-mistral-7b-chat, openbuddy-zephyr-7b-chat, openbuddy-deepseek-67b-chat.
218230
- [mistral](https://github.com/mistralai/mistral-src) 系列: mistral-7b, mistral-7b-instruct, mistral-7b-instruct-v2.

‎docs/source/LLM/支持的模型和数据集.md‎

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -42,18 +42,18 @@
4242
|qwen1half-7b-chat|[qwen/Qwen1.5-7B-Chat](https://modelscope.cn/models/qwen/Qwen1.5-7B-Chat/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|transformers>=4.37|
4343
|qwen1half-14b-chat|[qwen/Qwen1.5-14B-Chat](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|transformers>=4.37|
4444
|qwen1half-72b-chat|[qwen/Qwen1.5-72B-Chat](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|transformers>=4.37|
45-
|qwen1half-0_5b-chat-int8|[qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
4645
|qwen1half-0_5b-chat-int4|[qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
47-
|qwen1half-1_8b-chat-int8|[qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
4846
|qwen1half-1_8b-chat-int4|[qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
49-
|qwen1half-4b-chat-int8|[qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-4B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
5047
|qwen1half-4b-chat-int4|[qwen/Qwen1.5-4B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-4B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
51-
|qwen1half-7b-chat-int8|[qwen/Qwen1.5-7B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-7B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
5248
|qwen1half-7b-chat-int4|[qwen/Qwen1.5-7B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-7B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
53-
|qwen1half-14b-chat-int8|[qwen/Qwen1.5-14B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
5449
|qwen1half-14b-chat-int4|[qwen/Qwen1.5-14B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
55-
|qwen1half-72b-chat-int8|[qwen/Qwen1.5-72B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
5650
|qwen1half-72b-chat-int4|[qwen/Qwen1.5-72B-Chat-GPTQ-Int4](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat-GPTQ-Int4/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
51+
|qwen1half-0_5b-chat-int8|[qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
52+
|qwen1half-1_8b-chat-int8|[qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
53+
|qwen1half-4b-chat-int8|[qwen/Qwen1.5-4B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-4B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
54+
|qwen1half-7b-chat-int8|[qwen/Qwen1.5-7B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-7B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
55+
|qwen1half-14b-chat-int8|[qwen/Qwen1.5-14B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-14B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
56+
|qwen1half-72b-chat-int8|[qwen/Qwen1.5-72B-Chat-GPTQ-Int8](https://modelscope.cn/models/qwen/Qwen1.5-72B-Chat-GPTQ-Int8/summary)|q_proj, k_proj, v_proj|qwen|✔|✔|auto_gptq>=0.5, transformers>=4.37|
5757
|qwen-vl|[qwen/Qwen-VL](https://modelscope.cn/models/qwen/Qwen-VL/summary)|c_attn|default-generation|✔|✘||
5858
|qwen-vl-chat|[qwen/Qwen-VL-Chat](https://modelscope.cn/models/qwen/Qwen-VL-Chat/summary)|c_attn|qwen|✔|✘||
5959
|qwen-vl-chat-int4|[qwen/Qwen-VL-Chat-Int4](https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary)|c_attn|qwen|✔|✘|auto_gptq>=0.5|
@@ -119,10 +119,10 @@
119119
|baichuan-13b-chat|[baichuan-inc/Baichuan-13B-Chat](https://modelscope.cn/models/baichuan-inc/Baichuan-13B-Chat/summary)|W_pack|baichuan|&#x2718;|&#x2714;|transformers<4.34|
120120
|baichuan2-7b|[baichuan-inc/Baichuan2-7B-Base](https://modelscope.cn/models/baichuan-inc/Baichuan2-7B-Base/summary)|W_pack|default-generation|&#x2718;|&#x2714;||
121121
|baichuan2-7b-chat|[baichuan-inc/Baichuan2-7B-Chat](https://modelscope.cn/models/baichuan-inc/Baichuan2-7B-Chat/summary)|W_pack|baichuan|&#x2718;|&#x2714;||
122-
|baichuan2-7b-chat-int4|[baichuan-inc/Baichuan2-7B-Chat-4bits](https://modelscope.cn/models/baichuan-inc/Baichuan2-7B-Chat-4bits/summary)|W_pack|baichuan|&#x2718;|&#x2718;||
122+
|baichuan2-7b-chat-int4|[baichuan-inc/Baichuan2-7B-Chat-4bits](https://modelscope.cn/models/baichuan-inc/Baichuan2-7B-Chat-4bits/summary)|W_pack|baichuan|&#x2718;|&#x2718;|bitsandbytes<0.41.2, accelerate<0.26|
123123
|baichuan2-13b|[baichuan-inc/Baichuan2-13B-Base](https://modelscope.cn/models/baichuan-inc/Baichuan2-13B-Base/summary)|W_pack|default-generation|&#x2718;|&#x2714;||
124124
|baichuan2-13b-chat|[baichuan-inc/Baichuan2-13B-Chat](https://modelscope.cn/models/baichuan-inc/Baichuan2-13B-Chat/summary)|W_pack|baichuan|&#x2718;|&#x2714;||
125-
|baichuan2-13b-chat-int4|[baichuan-inc/Baichuan2-13B-Chat-4bits](https://modelscope.cn/models/baichuan-inc/Baichuan2-13B-Chat-4bits/summary)|W_pack|baichuan|&#x2718;|&#x2718;||
125+
|baichuan2-13b-chat-int4|[baichuan-inc/Baichuan2-13B-Chat-4bits](https://modelscope.cn/models/baichuan-inc/Baichuan2-13B-Chat-4bits/summary)|W_pack|baichuan|&#x2718;|&#x2718;|bitsandbytes<0.41.2, accelerate<0.26|
126126
|yuan2-2b-instruct|[YuanLLM/Yuan2.0-2B-hf](https://modelscope.cn/models/YuanLLM/Yuan2.0-2B-hf/summary)|q_proj, k_proj, v_proj|yuan|&#x2714;|&#x2718;||
127127
|yuan2-2b-janus-instruct|[YuanLLM/Yuan2-2B-Janus-hf](https://modelscope.cn/models/YuanLLM/Yuan2-2B-Janus-hf/summary)|q_proj, k_proj, v_proj|yuan|&#x2714;|&#x2718;||
128128
|yuan2-51b-instruct|[YuanLLM/Yuan2.0-51B-hf](https://modelscope.cn/models/YuanLLM/Yuan2.0-51B-hf/summary)|q_proj, k_proj, v_proj|yuan|&#x2714;|&#x2718;||

‎scripts/utils/run_model_info.py‎

Lines changed: 0 additions & 50 deletions
Original file line numberDiff line numberDiff line change
@@ -45,55 +45,5 @@ def get_model_info_table() -> List[str]:
4545
return res
4646

4747

48-
def get_model_info_readme_zh(data: List[str]) -> None:
49-
fpath = 'README_CN.md'
50-
with open(fpath, 'r') as f:
51-
text = f.read()
52-
start_idx = text.find(' - 多模态:')
53-
end_idx = text.find('- 支持的数据集:')
54-
text = text[start_idx:end_idx]
55-
match_list = re.findall(r'- (.+)( 系列)?: (.+)', text)
56-
model_list = []
57-
for match in match_list:
58-
model_list += match[2].strip('.').split(',')
59-
model_list_2 = []
60-
for model in model_list:
61-
model = model.strip()
62-
model_match = re.search(r'\[(.+)\]\(.+\)', model)
63-
if model_match is not None:
64-
model = model_match.group(1)
65-
model_list_2.append(model)
66-
model_list = model_list_2
67-
model_type_list = [d[0] for d in data]
68-
print(set(model_type_list) - set(model_list))
69-
print(set(model_list) - set(model_type_list))
70-
71-
72-
def get_model_info_readme_en(data: List[str]) -> None:
73-
fpath = 'README.md'
74-
with open(fpath, 'r') as f:
75-
raw_text = f.read()
76-
start_idx = raw_text.find(' - Multi-Modal:')
77-
end_idx = raw_text.find('- Supported Datasets:')
78-
text = raw_text[start_idx:end_idx]
79-
match_list = re.findall(r'- (.+)( series)?: (.+)', text)
80-
model_list = []
81-
for match in match_list:
82-
model_list += match[2].strip('.').split(',')
83-
model_list_2 = []
84-
for model in model_list:
85-
model = model.strip()
86-
model_match = re.search(r'\[(.+)\]\(.+\)', model)
87-
if model_match is not None:
88-
model = model_match.group(1)
89-
model_list_2.append(model)
90-
model_list = model_list_2
91-
model_type_list = [d[0] for d in data]
92-
print(set(model_type_list) - set(model_list))
93-
print(set(model_list) - set(model_type_list))
94-
95-
9648
if __name__ == '__main__':
9749
result = get_model_info_table()
98-
result_en = get_model_info_readme_en(result)
99-
result_zh = get_model_info_readme_zh(result)

‎swift/llm/deploy.py‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -121,6 +121,9 @@ async def inference_vllm_async(request: Union[ChatCompletionRequest,
121121
tokenizer = template.tokenizer
122122
if tokenizer.eos_token is not None and tokenizer.eos_token not in generation_config.stop:
123123
generation_config.stop.append(tokenizer.eos_token)
124+
if isinstance(template.suffix[-1],
125+
str) and template.suffix[-1] not in generation_config.stop:
126+
generation_config.stop.append(template.suffix[-1])
124127
created_time = int(time.time())
125128
result_generator = llm_engine.generate(None, generation_config, request_id,
126129
input_ids)

0 commit comments

Comments
 (0)