diff options
Diffstat (limited to 'examples/server')
| -rw-r--r-- | examples/server/server.cpp | 2 | ||||
| -rw-r--r-- | examples/server/utils.hpp | 4 |
2 files changed, 1 insertions, 5 deletions
diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 634e653a..25bc2963 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -1201,7 +1201,7 @@ struct server_context { }); } - if (result.tok == llama_token_eos(model)) { + if (llama_token_is_eog(model, result.tok)) { slot.stopped_eos = true; slot.has_next_token = false; diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp index a8d43ac6..1a221250 100644 --- a/examples/server/utils.hpp +++ b/examples/server/utils.hpp @@ -381,10 +381,6 @@ static json oaicompat_completion_params_parse( } else { llama_params["stop"] = json_value(body, "stop", json::array()); } - // Some chat templates don't use EOS token to stop generation - // We must add their end sequences to list of stop words - llama_params["stop"].push_back("<|im_end|>"); // chatml - llama_params["stop"].push_back("<end_of_turn>"); // gemma // Handle "response_format" field if (body.contains("response_format")) { |