haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

server : allow to specify tokens as strings in logit_bias (#5003)

Browse source 
* server: allow to specify tokens as strings in logit_bias

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Alexey Parfenov 2024-02-11 13:38:14 +00:00 committed by GitHub
parent 85910c5b30
commit 684780141a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 26 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
examples/server/README.md
View file

@ -185,7 +185,7 @@ node index.js
`ignore_eos`: Ignore end of stream token and continue generating (default: false).
`logit_bias`: Modify the likelihood of a token appearing in the generated text completion. For example, use `"logit_bias": [[15043,1.0]]` to increase the likelihood of the token 'Hello', or `"logit_bias": [[15043,-1.0]]` to decrease its likelihood. Setting the value to false, `"logit_bias": [[15043,false]]` ensures that the token `Hello` is never produced (default: []).
`logit_bias`: Modify the likelihood of a token appearing in the generated text completion. For example, use `"logit_bias": [[15043,1.0]]` to increase the likelihood of the token 'Hello', or `"logit_bias": [[15043,-1.0]]` to decrease its likelihood. Setting the value to false, `"logit_bias": [[15043,false]]` ensures that the token `Hello` is never produced. The tokens can also be represented as strings, e.g. `[["Hello, World!",-0.5]]` will reduce the likelihood of all the individual tokens that represent the string `Hello, World!`, just like the `presence_penalty` does. (default: []).
`n_probs`: If greater than 0, the response also contains the probabilities of top N tokens for each generated token (default: 0)

32
examples/server/server.cpp
View file

@ -626,18 +626,36 @@ struct llama_server_context
const int n_vocab = llama_n_vocab(model);
for (const auto &el : *logit_bias)
{
if (el.is_array() && el.size() == 2 && el[0].is_number_integer())
if (el.is_array() && el.size() == 2)
{
llama_token tok = el[0].get<llama_token>();
if (tok >= 0 && tok < n_vocab)
float bias;
if (el[1].is_number())
{
if (el[1].is_number())
bias = el[1].get<float>();
}
else if (el[1].is_boolean() && !el[1].get<bool>())
{
bias = -INFINITY;
}
else
{
continue;
}
if (el[0].is_number_integer())
{
llama_token tok = el[0].get<llama_token>();
if (tok >= 0 && tok < n_vocab)
{
slot->sparams.logit_bias[tok] = el[1].get<float>();
slot->sparams.logit_bias[tok] = bias;
}
else if (el[1].is_boolean() && !el[1].get<bool>())
}
else if (el[0].is_string())
{
auto toks = llama_tokenize(model, el[0].get<std::string>(), false);
for (auto tok : toks)
{
slot->sparams.logit_bias[tok] = -INFINITY;
slot->sparams.logit_bias[tok] = bias;
}
}
}