Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

server : add min_p param (#3877)

Browse Source 
* Update server.cpp with min_p after it was introduced in https://github.com/ggerganov/llama.cpp/pull/3841

* Use spaces instead of tabs

* Update index.html.hpp after running deps.sh

* Fix test - fix line ending
This commit is contained in:
Mihai 2023-11-09 04:00:34 +02:00 committed by GitHub
parent 875fb42871
commit 57ad015dc3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 2211 additions and 2191 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/README.md
View File

@ -122,6 +122,8 @@ node index.js
`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).
`min_p`: The minimum probability for a token to be considered, relative to the probability of the most likely token (default: 0.05).
`n_predict`: Set the maximum number of tokens to predict when generating text. **Note:** May exceed the set limit slightly if the last token is a partial multibyte character. When 0, no tokens will be generated but the prompt is evaluated into the cache. (default: -1, -1 = infinity). `n_predict`: Set the maximum number of tokens to predict when generating text. **Note:** May exceed the set limit slightly if the last token is a partial multibyte character. When 0, no tokens will be generated but the prompt is evaluated into the cache. (default: -1, -1 = infinity).
`n_keep`: Specify the number of tokens from the prompt to retain when the context size is exceeded and tokens need to be discarded. `n_keep`: Specify the number of tokens from the prompt to retain when the context size is exceeded and tokens need to be discarded.

4396
examples/server/index.html.hpp
View File

File diff suppressed because it is too large Load Diff

2
examples/server/public/index.html
View File

@ -219,6 +219,7 @@
repeat_penalty: 1.18, // 1.0 = disabled repeat_penalty: 1.18, // 1.0 = disabled
top_k: 40, // <= 0 to use vocab size top_k: 40, // <= 0 to use vocab size
top_p: 0.5, // 1.0 = disabled top_p: 0.5, // 1.0 = disabled
min_p: 0.05, // 0 = disabled
tfs_z: 1.0, // 1.0 = disabled tfs_z: 1.0, // 1.0 = disabled
typical_p: 1.0, // 1.0 = disabled typical_p: 1.0, // 1.0 = disabled
presence_penalty: 0.0, // 0.0 = disabled presence_penalty: 0.0, // 0.0 = disabled
@ -744,6 +745,7 @@
${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })} ${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
${IntField({ label: "Top-K sampling", max: 100, min: -1, name: "top_k", value: params.value.top_k })} ${IntField({ label: "Top-K sampling", max: 100, min: -1, name: "top_k", value: params.value.top_k })}
${FloatField({ label: "Top-P sampling", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p })} ${FloatField({ label: "Top-P sampling", max: 1.0, min: 0.0, name: "top_p", step: 0.01, value: params.value.top_p })}
${FloatField({ label: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}
</fieldset> </fieldset>
<details> <details>
<summary>More options</summary> <summary>More options</summary>

2
examples/server/server.cpp
View File

@ -679,6 +679,7 @@ struct llama_server_context
slot->params.n_predict = json_value(data, "n_predict", default_params.n_predict); slot->params.n_predict = json_value(data, "n_predict", default_params.n_predict);
slot->sparams.top_k = json_value(data, "top_k", default_sparams.top_k); slot->sparams.top_k = json_value(data, "top_k", default_sparams.top_k);
slot->sparams.top_p = json_value(data, "top_p", default_sparams.top_p); slot->sparams.top_p = json_value(data, "top_p", default_sparams.top_p);
slot->sparams.min_p = json_value(data, "min_p", default_sparams.min_p);
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);
@ -1113,6 +1114,7 @@ struct llama_server_context
{"temp", slot.sparams.temp}, {"temp", slot.sparams.temp},
{"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},
{"tfs_z", slot.sparams.tfs_z}, {"tfs_z", slot.sparams.tfs_z},
{"typical_p", slot.sparams.typical_p}, {"typical_p", slot.sparams.typical_p},
{"repeat_last_n", slot.sparams.penalty_last_n}, {"repeat_last_n", slot.sparams.penalty_last_n},