tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 12:19:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : add openai-style logit_bias support (#14946)

Browse Source 
Signed-off-by: Lukas Straub <lukasstraub2@web.de>
This commit is contained in:
Lukas Straub
2025-07-31 14:08:23 +02:00
committed by GitHub
parent 8a4a856277
commit a9f77a8be3
4 changed files with 90 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/README.md
View File

@@ -469,7 +469,7 @@ These words will not be included in the completion, so make sure to add them to
`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. 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: `[]`
`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. For compatibility with the OpenAI API, a JSON object {"<string or token id>": bias, ...} can also be passed. Default: `[]`
`n_probs`: If greater than 0, the response also contains the probabilities of top N tokens for each generated token given the sampling settings. Note that for temperature < 0 the tokens are sampled greedily but token probabilities are still being calculated via a simple softmax of the logits without considering any other sampler settings. Default: `0`