googleapis / googleapis/python-aiplatform
tests.system.vertexai.test_tokenization.TestTokenization: many tests failed
- 主要语言
- Python
- 星标
- 905
- 派生
- 465
- 平均合并
- 1 天 13 小时
- 30 天内合并 PR
- 44
描述
Many tests failed at the same time in this package.
* I will close this issue when there are no more failures in this package _and_
there is at least one pass.
* No new issues will be filed for this package until this issue is closed.
* If there are already issues for individual test cases, I will close them when
the corresponding test passes. You can close them earlier, if you prefer, and
I won't reopen them while this issue is still open.
Here are the tests that failed:
* test_count_tokens_local[_get_tokenizer_for_model_preview-gemini-1.5-pro-002-udhr-udhr-PROD_ENDPOINT] (#4624)
* test_count_tokens_local[get_tokenizer_for_model-gemini-1.5-pro-002-udhr-udhr-PROD_ENDPOINT]
* test_compute_tokens[_get_tokenizer_for_model_preview-gemini-1.5-pro-002-udhr-udhr-PROD_ENDPOINT]
* test_compute_tokens[get_tokenizer_for_model-gemini-1.5-pro-002-udhr-udhr-PROD_ENDPOINT] (#4625)
* test_count_tokens_system_instruction[gemini-1.5-pro-002-PROD_ENDPOINT]
* test_count_tokens_system_instruction_is_function_call[gemini-1.5-pro-002-PROD_ENDPOINT]
* test_count_tokens_system_instruction_is_function_response[gemini-1.5-pro-002-PROD_ENDPOINT]
* test_count_tokens_tool_is_function_declaration[gemini-1.5-pro-002-PROD_ENDPOINT]
* test_count_tokens_content_is_function_call[gemini-1.5-pro-002-PROD_ENDPOINT]
* test_count_tokens_content_is_function_response[gemini-1.5-pro-002-PROD_ENDPOINT]
-----
commit: ac5a5e4dd07890d07a553218d42040a6136fbb41
buildURL: [Build Status](https://source.cloud.google.com/results/invocations/0826b007-d9af-4e60-8584-d03c9cac927a), [Sponge](http://sponge2/0826b007-d9af-4e60-8584-d03c9cac927a)
status: failed
贡献指南
调研方向
Start with tests.system.vertexai.test_tokenization.TestTokenization and reproduce the listed failures at commit ac5a5e4dd07890d07a553218d42040a6136fbb41. Review the failed tokenization cases for gemini-1.5-pro-002, including system instructions, function calls, function responses, and tools. Done means this package has no failures and at least one passing test.
由索引模型根据 Issue 内容生成。
评估
- 技术栈
- python
- 领域
- machine-learning, testing-qa
- Issue 类型
- 缺陷
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 活跃度
- 冷清
- 描述清晰度
- 需要澄清
- 新手友好度
- 35/100