main: add options for temperature control #2088
Merged
+9
−1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ziegenberg
force-pushed
the
add-temperature
branch
2 times, most recently
from
c41ad26
to
7092144
Compare
|
I rebased and pushed. |
ziegenberg
force-pushed
the
add-temperature
branch
from
7092144
to
ec772e9
Compare
Add two options: ``` -tp, --temperature N [0.00 ] The sampling temperature, between 0 and 1 -tpi, --temperature-inc N [0.20 ] The increment of temperature, between 0 and 1 ``` The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit. Signed-off-by: Daniel Ziegenberg <[email protected]>
ziegenberg
force-pushed
the
add-temperature
branch
from
ec772e9
to
a0c7006
Compare
ggerganov
approved these changes
May 13, 2024
bygreencn
added a commit
to bygreencn/whisper.cpp
that referenced
this pull request
May 14, 2024
* ggerganov/master: (291 commits) whisper : fix model path encoding in windows (ggerganov#2086) server : return utf-8 (ggerganov#2138) node : add audio_ctx and audio buffer params (ggerganov#2123) cmake : fix HIP/ROCm build (ggerganov#2102) node : add additional params (ggerganov#2000) js : remove un-needed request header from fetchRemote (ggerganov#2119) cmake : fix metal embed sources path (ggerganov#2110) main : dont print timings with --no-prints (ggerganov#2108) main : add options for temperature control (ggerganov#2088) whisper : switch back to F32 mask (#0) whisper.android : update example, add field to print timestamp (ggerganov#2072) cmake : fix json INTERFACE library (ggerganov#2069) main : fix double quote escaping in csv output (ggerganov#2090) metal : tune soft_max number of threads (#0) whisper : remove old flash attn code (#0) ggml : try fix ppc64 (#0) ggml : remove oboslete alibi code (skipme) (#0) talk-llama : sync llama.cpp sync : ggml ggml : optimize for ppc64le using VSX intrinsics (ggml/784) ...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add two options: