ollama/docs
Quinn Slack f4432e1dba
treat stop as stop sequences, not exact tokens (#442)
The `stop` option to the generate API is a list of sequences that should cause generation to stop. Although these are commonly called "stop tokens", they do not necessarily correspond to LLM tokens (per the LLM's tokenizer). For example, if the caller sends a generate request with `"stop":["\n"]`, then generation should stop on any token containing `\n` (and trim `\n` from the output), not just if the token exactly matches `\n`. If `stop` were interpreted strictly as LLM tokens, then it would require callers of the generate API to know the LLM's tokenizer and enumerate many tokens in the `stop` list.

Fixes https://github.com/jmorganca/ollama/issues/295.
2023-08-30 11:53:42 -04:00
..
tutorials Update langchainpy.md 2023-08-14 12:12:56 +03:00
api.md update orca to orca-mini 2023-08-27 13:26:30 -04:00
development.md update README.md 2023-08-25 11:44:25 -07:00
faq.md cmd: use environment variables for server options 2023-08-10 14:17:53 -07:00
modelfile.md treat stop as stop sequences, not exact tokens (#442) 2023-08-30 11:53:42 -04:00
README.md Add tutorials for using Langchain with ollama 2023-08-10 21:27:37 -07:00
tutorials.md resolving bmacd comment 2023-08-11 13:51:44 -07:00