|
ember.cpp 0.1.0
C++ inference engine for Llama-family and paperkiln models (CPU, CUDA, WebAssembly)
|

Public Attributes | |
| ember::Conversation | conv |
| int | max_new_tokens = 60 |
| float | temperature = 0.1f |
| int | top_k = 40 |
| float | top_p = 0.9f |
| bool | has_seed = false |
| unsigned | seed = 0 |
| bool | want_ids = false |
| float | repeat_penalty = 1.0f |
| int | repeat_last_n = 64 |
Definition at line 83 of file server.cpp.
| ember::Conversation BpeChatRequest::conv |
Definition at line 84 of file server.cpp.
Referenced by main().
Definition at line 89 of file server.cpp.
| int BpeChatRequest::max_new_tokens = 60 |
Definition at line 85 of file server.cpp.
| int BpeChatRequest::repeat_last_n = 64 |
Definition at line 93 of file server.cpp.
| float BpeChatRequest::repeat_penalty = 1.0f |
Definition at line 92 of file server.cpp.
| unsigned BpeChatRequest::seed = 0 |
Definition at line 90 of file server.cpp.
Definition at line 86 of file server.cpp.
Referenced by main().
| int BpeChatRequest::top_k = 40 |
Definition at line 87 of file server.cpp.
Definition at line 88 of file server.cpp.
Definition at line 91 of file server.cpp.