26_14:52:31:900_linaro@aibox-1684x:/data/bmodels/LLM$ grep ^C 26_14:52:33:024_linaro@aibox-1684x:/data/bmodels/LLM$ ll 26_14:52:33:032_total 2730436 26_14:52:33:033_drwxrwxr-x 2 linaro linaro 4096 Dec 26 10:51 ./ 26_14:52:33:033_drwxrwxr-x 3 linaro linaro 4096 May 22 2024 ../ 26_14:52:33:033_-rw-r--r-- 1 linaro linaro 1473133908 May 22 2024 qwen1.5-1.8b_int4_1024.bmodel-def 26_14:52:33:033_-rw-r--r-- 1 linaro linaro 1322814052 Dec 26 10:33 qwen2.5-1.5b_int4_seq512_1dev.bmodel 26_14:52:44:908_linaro@aibox-1684x:/data/bmodels/LLM$ grep qwen1.5-1.8b_int4_1024 /firefly_services/ -r 26_14:54:27:431_linaro@aibox-1684x:/data/bmodels/LLM$ grep qwen1.5-1.8b_int4_1024 /firefly_services/FireflyChat/^Cr 26_14:54:27:617_linaro@aibox-1684x:/data/bmodels/LLM$ ^C 26_14:54:30:213_linaro@aibox-1684x:/data/bmodels/LLM$ vi /firefly_services/FireflyChat/ 26_14:54:30:213_.git/ CITATION.cff README.md configs/ modules/ run.sh web_assets/ 26_14:54:30:213_.github/ FireflyChat.py config.json history/ requirements.txt templates/ 26_14:54:30:213_.gitignore LICENSE config_example.json locale/ requirements_advanced.txt venv/ 26_14:54:33:321_linaro@aibox-1684x:/data/bmodels/LLM$ vi /firefly_services/FireflyChat/config 26_14:54:33:321_config.json config_example.json configs/ 26_14:54:35:834_linaro@aibox-1684x:/data/bmodels/LLM$ vi /firefly_services/FireflyChat/config.json 26_14:54:35:888_{ 26_14:54:35:888_ "local_embedding": true, 26_14:54:35:889_ "server_name": "0.0.0.0", 26_14:54:35:889_ "server_port": 7860, 26_14:54:35:889_ "share": false, 26_14:54:35:889_ "autobrowser": false, 26_14:54:35:890_ "language": "zh_CN", 26_14:54:35:890_ "hide_my_key": true, 26_14:54:35:891_ "chat_name_method_index": 1 26_14:54:35:891_} 26_14:56:38:946_linaro@aibox-1684x:/data/bmodels/LLM$ journalctl -xu ^C 26_14:56:39:114_linaro@aibox-1684x:/data/bmodels/LLM$ ^C 26_14:56:41:236_linaro@aibox-1684x:/data/bmodels/LLM$ sudo journalctl -u FireflyChat 26_14:56:41:546_-- Logs begin at Wed 2024-12-04 18:03:43 CST, end at Thu 2024-12-26 14:56:40 CST. -- 26_14:56:41:546_Dec 04 18:19:24 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:547_Dec 04 18:19:38 aibox-1684x run.sh[419]: 2024-12-04 18:19:38,332 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:56:41:548_Dec 04 18:19:45 aibox-1684x run.sh[419]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:56:41:548_Dec 04 18:19:45 aibox-1684x run.sh[419]: warnings.warn( 26_14:56:41:548_Dec 04 18:21:32 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:56:41:548_Dec 04 18:21:32 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:56:41:548_Dec 04 18:21:32 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:56:41:548_-- Reboot -- 26_14:56:41:549_Dec 15 14:44:42 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:549_Dec 15 14:44:55 aibox-1684x run.sh[414]: 2024-12-15 14:44:55,584 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:56:41:549_-- Reboot -- 26_14:56:41:549_Dec 15 14:45:33 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:550_Dec 15 14:45:46 aibox-1684x run.sh[411]: 2024-12-15 14:45:46,584 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:56:41:550_Dec 15 14:45:53 aibox-1684x run.sh[411]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:56:41:550_Dec 15 14:45:53 aibox-1684x run.sh[411]: warnings.warn( 26_14:56:41:550_Dec 15 15:12:06 aibox-1684x run.sh[411]: 2024-12-15 15:12:06,557 [INFO] [font_manager.py:1547] generated new fontManager 26_14:56:41:551_Dec 15 15:12:09 aibox-1684x run.sh[411]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:56:41:551_Dec 15 15:12:13 aibox-1684x run.sh[411]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:56:41:552_Dec 15 15:12:44 aibox-1684x run.sh[411]: 2024-12-15 15:12:44,205 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-12.json 26_14:56:41:552_Dec 15 15:12:47 aibox-1684x run.sh[411]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:56:41:552_Dec 15 15:12:47 aibox-1684x run.sh[411]: 2024-12-15 15:12:47,539 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-12.json 26_14:56:41:553_Dec 15 15:13:05 aibox-1684x run.sh[411]: 2024-12-15 15:13:05,858 [INFO] [base_model.py:611] 用户的输入为：你是由谁制造的 26_14:56:41:571_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,759 [INFO] [base_model.py:699] 回答为：我是由阿里云开发的超大规模语言模型——通义千问。作为一个AI助手，我的开发和训练主要由阿里云的工程师和科学家们进行。他们是通义千问的开发> 26_14:56:41:572_Dec 15 15:13:22 aibox-1684x run.sh[411]: 在制造过程中，通义千问主要采用了以下技术： 26_14:56:41:579_Dec 15 15:13:22 aibox-1684x run.sh[411]: 1. **深度学习模型**：通义千问使用了经过大规模训练的Transformer模型进行训练，这是一种基于Transformer架构的神经网络模型，能够有效地处理大量文本数据，并从中提取模式和知识。这种模型能够在多种任务> 26_14:56:41:590_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2. **语言模型训练**：通义千问的训练过程中会使用大量的语言数据进行训练，包括中文文本和英文文本，以提高模型的语义理解和生成能力。通过大规模的数据集和复杂的语言模型网络架构，通义千问可以捕捉到大> 26_14:56:41:599_Dec 15 15:13:22 aibox-1684x run.sh[411]: 3. **预训练模型**：为了提高通义千问在跨语言问题解答方面的精度，我在训练过程中还使用了一种预训练模型，如OpenAI的GPT-3。这个预训练模型具有很强的语言理解和生成能力，通过对大量的语言数据进行大规 > 26_14:56:41:609_Dec 15 15:13:22 aibox-1684x run.sh[411]: 4. **自动特征工程**：在模型训练过程中，还会进行一些自动特征工程的过程，例如词嵌入和上下文关系提取等，这些步骤能够帮助模型更好地理解和描述问题中的实体和关系，从而提高问题的回答质量。 26_14:56:41:622_Dec 15 15:13:22 aibox-1684x run.sh[411]: 在制造过程中，通义千问与大量的阿里云技术团队紧密合作，他们共同维护和更新模型的性能，优化模型的训练流程，以确保通义千问能够在各种环境下提供最优的性能和用户体验。 26_14:56:41:623_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,760 [INFO] [base_model.py:705] Tokens per second：23.44019452541218 26_14:56:41:624_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,760 [INFO] [base_model.py:725] Token 计数: 396，本次对话累计生成了 396 tokens 26_14:56:41:625_Dec 15 15:28:42 aibox-1684x run.sh[411]: 2024-12-15 15:28:42,098 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-28 26_14:56:41:625_-- Reboot -- 26_14:56:41:625_Dec 16 09:02:09 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:625_Dec 16 09:02:22 aibox-1684x run.sh[414]: 2024-12-16 09:02:22,851 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:56:41:625_Dec 16 09:02:30 aibox-1684x run.sh[414]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:56:41:626_Dec 16 09:02:30 aibox-1684x run.sh[414]: warnings.warn( 26_14:56:41:626_-- Reboot -- 26_14:56:41:626_Dec 22 14:48:11 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:627_Dec 22 14:48:25 aibox-1684x run.sh[410]: 2024-12-22 14:48:25,051 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:56:41:627_Dec 22 14:48:32 aibox-1684x run.sh[410]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:56:41:627_Dec 22 14:48:32 aibox-1684x run.sh[410]: warnings.warn( 26_14:56:41:627_Dec 22 15:25:48 aibox-1684x run.sh[410]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:56:41:628_Dec 22 15:25:49 aibox-1684x run.sh[410]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:56:41:629_Dec 22 15:26:20 aibox-1684x run.sh[410]: 2024-12-22 15:26:20,508 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26.json 26_14:56:41:629_Dec 22 15:26:22 aibox-1684x run.sh[410]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:56:41:629_Dec 22 15:26:22 aibox-1684x run.sh[410]: 2024-12-22 15:26:22,117 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26.json 26_14:56:41:630_Dec 22 15:26:22 aibox-1684x run.sh[410]: 2024-12-22 15:26:22,222 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:56:41:631_Dec 22 15:26:30 aibox-1684x run.sh[410]: 2024-12-22 15:26:30,701 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:56:41:631_Dec 22 15:59:21 aibox-1684x run.sh[410]: 2024-12-22 15:59:21,254 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:56:41:632_Dec 22 15:59:58 aibox-1684x run.sh[410]: 2024-12-22 15:59:58,703 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-59 26_14:56:41:632_Dec 22 16:13:53 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:56:41:632_Dec 22 16:13:54 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:56:41:632_Dec 22 16:13:54 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:56:41:632_-- Reboot -- 26_14:56:41:632_Dec 22 16:14:16 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:56:41:632_Dec 22 16:14:25 aibox-1684x run.sh[409]: 2024-12-22 16:14:25,525 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:57:21:831_Dec 22 16:14:29 aibox-1684x run.sh[409]: 2024-12-22 16:14:29,906 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:57:21:831_Dec 22 16:14:37 aibox-1684x run.sh[409]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:57:21:831_Dec 22 16:14:37 aibox-1684x run.sh[409]: warnings.warn( 26_14:57:21:832_Dec 22 16:14:40 aibox-1684x run.sh[409]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:57:21:832_Dec 22 16:14:42 aibox-1684x run.sh[409]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:57:21:832_Dec 22 16:15:43 aibox-1684x run.sh[409]: 2024-12-22 16:15:43,032 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-15.json 26_14:57:21:833_Dec 22 16:15:56 aibox-1684x run.sh[409]: 2024-12-22 16:15:56,706 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-15 26_14:57:21:833_Dec 22 16:16:10 aibox-1684x run.sh[409]: 2024-12-22 16:16:10,143 [INFO] [base_model.py:611] 用户的输入为：你是由谁开发的 26_14:57:21:834_Dec 22 16:16:10 aibox-1684x run.sh[400]: /firefly_services/FireflyChat/run.sh: line 6: 409 Segmentation fault python3 FireflyChat.py 26_14:57:21:834_Dec 22 16:16:10 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=139/n/a 26_14:57:21:834_Dec 22 16:16:10 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:57:21:834_Dec 22 16:16:13 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 1. 26_14:57:21:834_Dec 22 16:16:13 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:57:21:834_Dec 22 16:16:13 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:57:21:835_Dec 22 16:16:18 aibox-1684x run.sh[1529]: 2024-12-22 16:16:18,488 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:57:21:835_Dec 22 16:16:22 aibox-1684x run.sh[1529]: 2024-12-22 16:16:22,636 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:57:21:835_Dec 22 16:16:28 aibox-1684x run.sh[1529]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:57:21:835_Dec 22 16:16:28 aibox-1684x run.sh[1529]: warnings.warn( 26_14:57:21:836_Dec 22 16:16:31 aibox-1684x run.sh[1529]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:57:21:836_Dec 22 16:16:32 aibox-1684x run.sh[1529]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:57:21:836_Dec 22 16:16:37 aibox-1684x run.sh[1529]: 2024-12-22 16:16:37,224 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-16.json 26_14:57:21:849_Dec 22 16:16:37 aibox-1684x run.sh[1529]: 2024-12-22 16:16:37,328 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-16 26_14:57:21:851_Dec 22 16:22:42 aibox-1684x run.sh[1529]: 2024-12-22 16:22:42,171 [INFO] [base_model.py:611] 用户的输入为：单独的单独的多多 26_14:57:21:851_Dec 22 16:22:42 aibox-1684x run.sh[1528]: /firefly_services/FireflyChat/run.sh: line 6: 1529 Segmentation fault python3 FireflyChat.py 26_14:57:21:851_Dec 22 16:22:42 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=139/n/a 26_14:57:21:851_Dec 22 16:22:42 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:57:21:852_Dec 22 16:22:45 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 2. 26_14:57:21:852_Dec 22 16:22:45 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:57:21:852_Dec 22 16:22:45 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:57:21:852_Dec 22 16:22:50 aibox-1684x run.sh[2976]: 2024-12-22 16:22:50,527 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:57:21:852_Dec 22 16:22:54 aibox-1684x run.sh[2976]: 2024-12-22 16:22:54,583 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:57:21:853_Dec 22 16:23:00 aibox-1684x run.sh[2976]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:57:21:853_Dec 22 16:23:00 aibox-1684x run.sh[2976]: warnings.warn( 26_14:57:21:853_Dec 22 16:23:04 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:57:21:853_Dec 22 16:23:04 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:57:21:853_Dec 22 16:23:04 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:57:21:853_-- Reboot -- 26_14:57:21:853_Dec 23 09:53:37 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:57:21:854_Dec 23 09:53:51 aibox-1684x run.sh[412]: 2024-12-23 09:53:51,143 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:57:21:854_Dec 23 09:53:58 aibox-1684x run.sh[412]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:57:21:854_Dec 23 09:53:58 aibox-1684x run.sh[412]: warnings.warn( 26_14:57:21:854_Dec 23 09:55:05 aibox-1684x run.sh[412]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:57:21:855_Dec 23 09:55:06 aibox-1684x run.sh[412]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:57:21:855_Dec 23 09:56:07 aibox-1684x run.sh[412]: 2024-12-23 09:56:07,679 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-23 09-56.json 26_14:57:21:856_Dec 23 09:56:51 aibox-1684x run.sh[412]: 2024-12-23 09:56:51,672 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-23 09-56 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: Device [ 0 ] loading .... 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:498] INFO:cpu_lib 'libcpuop.so' is loaded. 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:521] INFO:Not able to open libcustomcpuop.so 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: bmcpu init: skip cpu_user_defined 26_14:57:21:856_Dec 26 14:54:48 aibox-1684x run.sh[412]: open usercpu.so, init user_cpu_init 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][BMProfileDeviceBase:190] INFO:gdma=0, tiu=0, mcu=0 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: Model[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] loading .... 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1939] INFO:Loading bmodel from [/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel]. Thanks for your patience... 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1704] INFO:Bmodel loaded, version 2.2+v1.10.beta.0-157-g5f64a6de8-20240912 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1706] INFO:pre net num: 0, load net num: 68 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_tpu_module:1802] INFO:loading firmare in bmodel 26_14:57:21:857_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][preload_funcs:2121] INFO: core_id=0, multi_fullnet_func_id=22 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][preload_funcs:2124] INFO: core_id=0, dynamic_fullnet_func_id=23 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: Done! 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmrt_get_network_info:450] WRONG:net name:greedy_head invalid 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmrt_get_network_info:450] WRONG:net name:penalty_sample_head invalid 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: Device [ 0 ] loading .... 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:498] INFO:cpu_lib 'libcpuop.so' is loaded. 26_14:57:22:269_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:521] INFO:Not able to open libcustomcpuop.so 26_14:57:22:270_Dec 26 14:54:48 aibox-1684x run.sh[412]: bmcpu init: skip cpu_user_defined 26_14:57:22:270_Dec 26 14:54:48 aibox-1684x run.sh[412]: open usercpu.so, init user_cpu_init 26_14:57:22:270_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][BMProfileDeviceBase:190] INFO:gdma=0, tiu=0, mcu=0 26_14:57:22:278_Dec 26 14:54:48 aibox-1684x run.sh[412]: Model[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] loading .... 26_14:57:22:278_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1939] INFO:Loading bmodel from [/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel]. Thanks for your patience... 26_14:57:22:279_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMODEL][ModelCtx:390] FATAL: File[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] open failed. 26_14:57:22:279_Dec 26 14:54:48 aibox-1684x run.sh[412]: python3: /home/linaro/firefly-ai/src/libc_qwen1_5.cpp:128: void Qwen::init(const std::vector&, std::string): Assertion `true == ret' failed. 26_14:57:22:279_Dec 26 14:54:48 aibox-1684x run.sh[402]: /firefly_services/FireflyChat/run.sh: line 6: 412 Aborted python3 FireflyChat.py 26_14:57:22:279_Dec 26 14:54:48 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=134/n/a 26_14:57:22:280_Dec 26 14:54:48 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:57:22:280_Dec 26 14:54:51 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 1. 26_14:57:22:280_Dec 26 14:54:51 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:57:22:280_Dec 26 14:54:51 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:57:22:281_Dec 26 14:55:00 aibox-1684x run.sh[715451]: 2024-12-26 14:55:00,367 [ERROR] [config.py:316] 你填写的默认模型Qwen1.5-1.8B不存在！请从下面的列表中挑一个填写：['No Model'] 26_14:57:22:281_Dec 26 14:55:06 aibox-1684x run.sh[715451]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:57:22:282_Dec 26 14:55:06 aibox-1684x run.sh[715451]: warnings.warn( 26_14:58:03:221_ 26_14:58:03:399_linaro@aibox-1684x:/data/bmodels/LLM$ ^C 26_14:58:03:570_linaro@aibox-1684x:/data/bmodels/LLM$ ^C 26_14:58:05:417_linaro@aibox-1684x:/data/bmodels/LLM$ sudo systemctl restart FireflyChat 26_14:58:06:225_linaro@aibox-1684x:/data/bmodels/LLM$ 26_14:58:06:401_linaro@aibox-1684x:/data/bmodels/LLM$ 26_14:58:08:537_linaro@aibox-1684x:/data/bmodels/LLM$ sudo journalctl -u FireflyChat 26_14:58:08:574_-- Logs begin at Wed 2024-12-04 18:03:43 CST, end at Thu 2024-12-26 14:58:07 CST. -- 26_14:58:08:574_Dec 04 18:19:24 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:575_Dec 04 18:19:38 aibox-1684x run.sh[419]: 2024-12-04 18:19:38,332 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:08:575_Dec 04 18:19:45 aibox-1684x run.sh[419]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:08:575_Dec 04 18:19:45 aibox-1684x run.sh[419]: warnings.warn( 26_14:58:08:576_Dec 04 18:21:32 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:58:08:576_Dec 04 18:21:32 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:58:08:576_Dec 04 18:21:32 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:08:576_-- Reboot -- 26_14:58:08:576_Dec 15 14:44:42 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:577_Dec 15 14:44:55 aibox-1684x run.sh[414]: 2024-12-15 14:44:55,584 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:08:577_-- Reboot -- 26_14:58:08:577_Dec 15 14:45:33 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:578_Dec 15 14:45:46 aibox-1684x run.sh[411]: 2024-12-15 14:45:46,584 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:08:578_Dec 15 14:45:53 aibox-1684x run.sh[411]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:08:578_Dec 15 14:45:53 aibox-1684x run.sh[411]: warnings.warn( 26_14:58:08:578_Dec 15 15:12:06 aibox-1684x run.sh[411]: 2024-12-15 15:12:06,557 [INFO] [font_manager.py:1547] generated new fontManager 26_14:58:08:578_Dec 15 15:12:09 aibox-1684x run.sh[411]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:08:579_Dec 15 15:12:13 aibox-1684x run.sh[411]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:08:589_Dec 15 15:12:44 aibox-1684x run.sh[411]: 2024-12-15 15:12:44,205 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-12.json 26_14:58:08:589_Dec 15 15:12:47 aibox-1684x run.sh[411]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:08:590_Dec 15 15:12:47 aibox-1684x run.sh[411]: 2024-12-15 15:12:47,539 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-12.json 26_14:58:08:591_Dec 15 15:13:05 aibox-1684x run.sh[411]: 2024-12-15 15:13:05,858 [INFO] [base_model.py:611] 用户的输入为：你是由谁制造的 26_14:58:08:605_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,759 [INFO] [base_model.py:699] 回答为：我是由阿里云开发的超大规模语言模型——通义千问。作为一个AI助手，我的开发和训练主要由阿里云的工程师和科学家们进行。他们是通义千问的开发> 26_14:58:08:606_Dec 15 15:13:22 aibox-1684x run.sh[411]: 在制造过程中，通义千问主要采用了以下技术： 26_14:58:08:614_Dec 15 15:13:22 aibox-1684x run.sh[411]: 1. **深度学习模型**：通义千问使用了经过大规模训练的Transformer模型进行训练，这是一种基于Transformer架构的神经网络模型，能够有效地处理大量文本数据，并从中提取模式和知识。这种模型能够在多种任务> 26_14:58:08:623_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2. **语言模型训练**：通义千问的训练过程中会使用大量的语言数据进行训练，包括中文文本和英文文本，以提高模型的语义理解和生成能力。通过大规模的数据集和复杂的语言模型网络架构，通义千问可以捕捉到大> 26_14:58:08:629_Dec 15 15:13:22 aibox-1684x run.sh[411]: 3. **预训练模型**：为了提高通义千问在跨语言问题解答方面的精度，我在训练过程中还使用了一种预训练模型，如OpenAI的GPT-3。这个预训练模型具有很强的语言理解和生成能力，通过对大量的语言数据进行大规 > 26_14:58:08:635_Dec 15 15:13:22 aibox-1684x run.sh[411]: 4. **自动特征工程**：在模型训练过程中，还会进行一些自动特征工程的过程，例如词嵌入和上下文关系提取等，这些步骤能够帮助模型更好地理解和描述问题中的实体和关系，从而提高问题的回答质量。 26_14:58:08:645_Dec 15 15:13:22 aibox-1684x run.sh[411]: 在制造过程中，通义千问与大量的阿里云技术团队紧密合作，他们共同维护和更新模型的性能，优化模型的训练流程，以确保通义千问能够在各种环境下提供最优的性能和用户体验。 26_14:58:08:646_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,760 [INFO] [base_model.py:705] Tokens per second：23.44019452541218 26_14:58:08:646_Dec 15 15:13:22 aibox-1684x run.sh[411]: 2024-12-15 15:13:22,760 [INFO] [base_model.py:725] Token 计数: 396，本次对话累计生成了 396 tokens 26_14:58:08:647_Dec 15 15:28:42 aibox-1684x run.sh[411]: 2024-12-15 15:28:42,098 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-15 15-28 26_14:58:08:647_-- Reboot -- 26_14:58:08:647_Dec 16 09:02:09 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:648_Dec 16 09:02:22 aibox-1684x run.sh[414]: 2024-12-16 09:02:22,851 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:08:648_Dec 16 09:02:30 aibox-1684x run.sh[414]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:08:648_Dec 16 09:02:30 aibox-1684x run.sh[414]: warnings.warn( 26_14:58:08:648_-- Reboot -- 26_14:58:08:648_Dec 22 14:48:11 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:649_Dec 22 14:48:25 aibox-1684x run.sh[410]: 2024-12-22 14:48:25,051 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:08:649_Dec 22 14:48:32 aibox-1684x run.sh[410]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:08:649_Dec 22 14:48:32 aibox-1684x run.sh[410]: warnings.warn( 26_14:58:08:649_Dec 22 15:25:48 aibox-1684x run.sh[410]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:08:649_Dec 22 15:25:49 aibox-1684x run.sh[410]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:08:650_Dec 22 15:26:20 aibox-1684x run.sh[410]: 2024-12-22 15:26:20,508 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26.json 26_14:58:08:650_Dec 22 15:26:22 aibox-1684x run.sh[410]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:08:651_Dec 22 15:26:22 aibox-1684x run.sh[410]: 2024-12-22 15:26:22,117 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26.json 26_14:58:08:651_Dec 22 15:26:22 aibox-1684x run.sh[410]: 2024-12-22 15:26:22,222 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:58:08:652_Dec 22 15:26:30 aibox-1684x run.sh[410]: 2024-12-22 15:26:30,701 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:58:08:653_Dec 22 15:59:21 aibox-1684x run.sh[410]: 2024-12-22 15:59:21,254 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-26 26_14:58:08:653_Dec 22 15:59:58 aibox-1684x run.sh[410]: 2024-12-22 15:59:58,703 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 15-59 26_14:58:08:654_Dec 22 16:13:53 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:58:08:654_Dec 22 16:13:54 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:58:08:654_Dec 22 16:13:54 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:08:654_-- Reboot -- 26_14:58:08:654_Dec 22 16:14:16 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:08:655_Dec 22 16:14:25 aibox-1684x run.sh[409]: 2024-12-22 16:14:25,525 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:58:09:797_Dec 22 16:14:29 aibox-1684x run.sh[409]: 2024-12-22 16:14:29,906 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:09:797_Dec 22 16:14:37 aibox-1684x run.sh[409]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:09:797_Dec 22 16:14:37 aibox-1684x run.sh[409]: warnings.warn( 26_14:58:09:798_Dec 22 16:14:40 aibox-1684x run.sh[409]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:09:798_Dec 22 16:14:42 aibox-1684x run.sh[409]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:09:798_Dec 22 16:15:43 aibox-1684x run.sh[409]: 2024-12-22 16:15:43,032 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-15.json 26_14:58:09:799_Dec 22 16:15:56 aibox-1684x run.sh[409]: 2024-12-22 16:15:56,706 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-15 26_14:58:09:800_Dec 22 16:16:10 aibox-1684x run.sh[409]: 2024-12-22 16:16:10,143 [INFO] [base_model.py:611] 用户的输入为：你是由谁开发的 26_14:58:09:800_Dec 22 16:16:10 aibox-1684x run.sh[400]: /firefly_services/FireflyChat/run.sh: line 6: 409 Segmentation fault python3 FireflyChat.py 26_14:58:09:800_Dec 22 16:16:10 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=139/n/a 26_14:58:09:800_Dec 22 16:16:10 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:58:09:800_Dec 22 16:16:13 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 1. 26_14:58:09:800_Dec 22 16:16:13 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:09:801_Dec 22 16:16:13 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:09:801_Dec 22 16:16:18 aibox-1684x run.sh[1529]: 2024-12-22 16:16:18,488 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:58:09:802_Dec 22 16:16:22 aibox-1684x run.sh[1529]: 2024-12-22 16:16:22,636 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:09:802_Dec 22 16:16:28 aibox-1684x run.sh[1529]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:09:802_Dec 22 16:16:28 aibox-1684x run.sh[1529]: warnings.warn( 26_14:58:09:802_Dec 22 16:16:31 aibox-1684x run.sh[1529]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:09:802_Dec 22 16:16:32 aibox-1684x run.sh[1529]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:09:803_Dec 22 16:16:37 aibox-1684x run.sh[1529]: 2024-12-22 16:16:37,224 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-16.json 26_14:58:09:817_Dec 22 16:16:37 aibox-1684x run.sh[1529]: 2024-12-22 16:16:37,328 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-22 16-16 26_14:58:09:817_Dec 22 16:22:42 aibox-1684x run.sh[1529]: 2024-12-22 16:22:42,171 [INFO] [base_model.py:611] 用户的输入为：单独的单独的多多 26_14:58:09:818_Dec 22 16:22:42 aibox-1684x run.sh[1528]: /firefly_services/FireflyChat/run.sh: line 6: 1529 Segmentation fault python3 FireflyChat.py 26_14:58:09:818_Dec 22 16:22:42 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=139/n/a 26_14:58:09:818_Dec 22 16:22:42 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:58:09:818_Dec 22 16:22:45 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 2. 26_14:58:09:818_Dec 22 16:22:45 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:09:818_Dec 22 16:22:45 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:09:819_Dec 22 16:22:50 aibox-1684x run.sh[2976]: 2024-12-22 16:22:50,527 [INFO] [_client.py:1026] HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 26_14:58:09:819_Dec 22 16:22:54 aibox-1684x run.sh[2976]: 2024-12-22 16:22:54,583 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:09:819_Dec 22 16:23:00 aibox-1684x run.sh[2976]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:09:819_Dec 22 16:23:00 aibox-1684x run.sh[2976]: warnings.warn( 26_14:58:09:820_Dec 22 16:23:04 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:58:09:820_Dec 22 16:23:04 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:58:09:820_Dec 22 16:23:04 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:09:820_-- Reboot -- 26_14:58:09:820_Dec 23 09:53:37 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:09:820_Dec 23 09:53:51 aibox-1684x run.sh[412]: 2024-12-23 09:53:51,143 [INFO] [config.py:314] 默认模型设置为了：Qwen1.5-1.8B 26_14:58:09:821_Dec 23 09:53:58 aibox-1684x run.sh[412]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:09:821_Dec 23 09:53:58 aibox-1684x run.sh[412]: warnings.warn( 26_14:58:09:821_Dec 23 09:55:05 aibox-1684x run.sh[412]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:09:821_Dec 23 09:55:06 aibox-1684x run.sh[412]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:09:822_Dec 23 09:56:07 aibox-1684x run.sh[412]: 2024-12-23 09:56:07,679 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-23 09-56.json 26_14:58:09:822_Dec 23 09:56:51 aibox-1684x run.sh[412]: 2024-12-23 09:56:51,672 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-23 09-56 26_14:58:09:822_Dec 26 14:54:48 aibox-1684x run.sh[412]: Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: Device [ 0 ] loading .... 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:498] INFO:cpu_lib 'libcpuop.so' is loaded. 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:521] INFO:Not able to open libcustomcpuop.so 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: bmcpu init: skip cpu_user_defined 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: open usercpu.so, init user_cpu_init 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][BMProfileDeviceBase:190] INFO:gdma=0, tiu=0, mcu=0 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: Model[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] loading .... 26_14:58:09:823_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1939] INFO:Loading bmodel from [/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel]. Thanks for your patience... 26_14:58:09:824_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1704] INFO:Bmodel loaded, version 2.2+v1.10.beta.0-157-g5f64a6de8-20240912 26_14:58:09:824_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1706] INFO:pre net num: 0, load net num: 68 26_14:58:09:824_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_tpu_module:1802] INFO:loading firmare in bmodel 26_14:58:09:824_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][preload_funcs:2121] INFO: core_id=0, multi_fullnet_func_id=22 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][preload_funcs:2124] INFO: core_id=0, dynamic_fullnet_func_id=23 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: Done! 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmrt_get_network_info:450] WRONG:net name:greedy_head invalid 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmrt_get_network_info:450] WRONG:net name:penalty_sample_head invalid 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: Device [ 0 ] loading .... 26_14:58:09:995_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:498] INFO:cpu_lib 'libcpuop.so' is loaded. 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][bmcpu_setup:521] INFO:Not able to open libcustomcpuop.so 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: bmcpu init: skip cpu_user_defined 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: open usercpu.so, init user_cpu_init 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][BMProfileDeviceBase:190] INFO:gdma=0, tiu=0, mcu=0 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: Model[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] loading .... 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMRT][load_bmodel:1939] INFO:Loading bmodel from [/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel]. Thanks for your patience... 26_14:58:09:996_Dec 26 14:54:48 aibox-1684x run.sh[412]: [BMODEL][ModelCtx:390] FATAL: File[/data/bmodels/LLM/qwen1.5-1.8b_int4_1024.bmodel] open failed. 26_14:58:09:997_Dec 26 14:54:48 aibox-1684x run.sh[412]: python3: /home/linaro/firefly-ai/src/libc_qwen1_5.cpp:128: void Qwen::init(const std::vector&, std::string): Assertion `true == ret' failed. 26_14:58:09:997_Dec 26 14:54:48 aibox-1684x run.sh[402]: /firefly_services/FireflyChat/run.sh: line 6: 412 Aborted python3 FireflyChat.py 26_14:58:09:997_Dec 26 14:54:48 aibox-1684x systemd[1]: FireflyChat.service: Main process exited, code=exited, status=134/n/a 26_14:58:10:009_Dec 26 14:54:48 aibox-1684x systemd[1]: FireflyChat.service: Failed with result 'exit-code'. 26_14:58:10:009_Dec 26 14:54:51 aibox-1684x systemd[1]: FireflyChat.service: Scheduled restart job, restart counter is at 1. 26_14:58:10:010_Dec 26 14:54:51 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:10:010_Dec 26 14:54:51 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:10:011_Dec 26 14:55:00 aibox-1684x run.sh[715451]: 2024-12-26 14:55:00,367 [ERROR] [config.py:316] 你填写的默认模型Qwen1.5-1.8B不存在！请从下面的列表中挑一个填写：['No Model'] 26_14:58:10:011_Dec 26 14:55:06 aibox-1684x run.sh[715451]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:10:011_Dec 26 14:55:06 aibox-1684x run.sh[715451]: warnings.warn( 26_14:58:10:011_Dec 26 14:58:04 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:58:10:012_Dec 26 14:58:04 aibox-1684x systemd[1]: FireflyChat.service: Killing process 715520 (python3) with signal SIGKILL. 26_14:58:10:012_Dec 26 14:58:04 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:58:10:012_Dec 26 14:58:04 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:10:012_Dec 26 14:58:04 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:33:940_ 26_14:58:34:151_linaro@aibox-1684x:/data/bmodels/LLM$ ^C 26_14:58:36:239_linaro@aibox-1684x:/data/bmodels/LLM$ sudo journalctl -fu FireflyChat 26_14:58:36:287_-- Logs begin at Wed 2024-12-04 18:03:43 CST. -- 26_14:58:36:287_Dec 26 14:55:06 aibox-1684x run.sh[715451]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:36:288_Dec 26 14:55:06 aibox-1684x run.sh[715451]: warnings.warn( 26_14:58:36:288_Dec 26 14:58:04 aibox-1684x systemd[1]: Stopping Firefly Chat... 26_14:58:36:288_Dec 26 14:58:04 aibox-1684x systemd[1]: FireflyChat.service: Killing process 715520 (python3) with signal SIGKILL. 26_14:58:36:288_Dec 26 14:58:04 aibox-1684x systemd[1]: FireflyChat.service: Succeeded. 26_14:58:36:288_Dec 26 14:58:04 aibox-1684x systemd[1]: Stopped Firefly Chat. 26_14:58:36:288_Dec 26 14:58:04 aibox-1684x systemd[1]: Started Firefly Chat. 26_14:58:36:289_Dec 26 14:58:13 aibox-1684x run.sh[715994]: 2024-12-26 14:58:13,185 [ERROR] [config.py:316] 你填写的默认模型Qwen1.5-1.8B不存在！请从下面的列表中挑一个填写：['No Model'] 26_14:58:36:289_Dec 26 14:58:19 aibox-1684x run.sh[715994]: /firefly_services/FireflyChat/venv/lib/python3.8/site-packages/gradio/utils.py:932: UserWarning: Expected maximum 4 arguments for function , received 8. 26_14:58:36:289_Dec 26 14:58:19 aibox-1684x run.sh[715994]: warnings.warn( 26_14:58:37:396_ 26_14:58:37:911_ 26_14:58:37:931_ 26_14:58:37:967_ 26_14:58:37:999_ 26_14:58:38:028_ 26_14:58:38:061_ 26_14:58:38:109_ 26_14:58:38:142_ 26_14:58:38:173_ 26_14:58:38:205_ 26_14:58:38:237_ 26_14:58:38:269_ 26_14:58:47:890_Dec 26 14:58:46 aibox-1684x run.sh[715994]: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. 26_14:58:47:891_Dec 26 14:58:46 aibox-1684x run.sh[715994]: 2024-12-26 14:58:46,672 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-26 14-58.json 26_14:58:48:386_Dec 26 14:58:47 aibox-1684x run.sh[715994]: 2024-12-26 14:58:47,028 [INFO] [base_model.py:1072] 没有找到对话历史记录 新对话 12-26 14-58 26_14:59:21:631_^C