Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 05:48:47 +01:00
Code Issues Packages Projects Releases Wiki Activity

server : add dynatemp_range and dynatemp_exponent (#5352)

Browse Source 
* server: added `dynatemp_range` and `dynatemp_exponent`

* Update README.md

---------

Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
This commit is contained in:
Michael Coppola 2024-02-06 04:20:00 -05:00 committed by GitHub
parent 4ffc7a17d4
commit 31e7903221
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 29 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/README.md
View File

@ -137,6 +137,10 @@ node index.js
`temperature`: Adjust the randomness of the generated text (default: 0.8). `temperature`: Adjust the randomness of the generated text (default: 0.8).
`dynatemp_range`: Dynamic temperature range (default: 0.0, 0.0 = disabled).
`dynatemp_exponent`: Dynamic temperature exponent (default: 1.0).
`top_k`: Limit the next token selection to the K most probable tokens (default: 40). `top_k`: Limit the next token selection to the K most probable tokens (default: 40).
`top_p`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.95). `top_p`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.95).

4
examples/server/server.cpp
View File

@ -533,6 +533,8 @@ struct llama_server_context
slot->sparams.tfs_z = json_value(data, "tfs_z", default_sparams.tfs_z); slot->sparams.tfs_z = json_value(data, "tfs_z", default_sparams.tfs_z);
slot->sparams.typical_p = json_value(data, "typical_p", default_sparams.typical_p); slot->sparams.typical_p = json_value(data, "typical_p", default_sparams.typical_p);
slot->sparams.temp = json_value(data, "temperature", default_sparams.temp); slot->sparams.temp = json_value(data, "temperature", default_sparams.temp);
slot->sparams.dynatemp_range = json_value(data, "dynatemp_range", default_sparams.dynatemp_range);
slot->sparams.dynatemp_exponent = json_value(data, "dynatemp_exponent", default_sparams.dynatemp_exponent);
slot->sparams.penalty_last_n = json_value(data, "repeat_last_n", default_sparams.penalty_last_n); slot->sparams.penalty_last_n = json_value(data, "repeat_last_n", default_sparams.penalty_last_n);
slot->sparams.penalty_repeat = json_value(data, "repeat_penalty", default_sparams.penalty_repeat); slot->sparams.penalty_repeat = json_value(data, "repeat_penalty", default_sparams.penalty_repeat);
slot->sparams.penalty_freq = json_value(data, "frequency_penalty", default_sparams.penalty_freq); slot->sparams.penalty_freq = json_value(data, "frequency_penalty", default_sparams.penalty_freq);
@ -1002,6 +1004,8 @@ struct llama_server_context
{"model", params.model_alias}, {"model", params.model_alias},
{"seed", slot.params.seed}, {"seed", slot.params.seed},
{"temperature", slot.sparams.temp}, {"temperature", slot.sparams.temp},
{"dynatemp_range", slot.sparams.dynatemp_range},
{"dynatemp_exponent", slot.sparams.dynatemp_exponent},
{"top_k", slot.sparams.top_k}, {"top_k", slot.sparams.top_k},
{"top_p", slot.sparams.top_p}, {"top_p", slot.sparams.top_p},
{"min_p", slot.sparams.min_p}, {"min_p", slot.sparams.min_p},