vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 00:54:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Full DynaTemp implementation + UI (#600)

Browse source 
* move Dynatemp changes to new branch

* fix float header

* Properly reintroduce variable expert count

Controllable through experts.txt

* first pass at DynaTemp UI

Checkbox partial implemented, Min and Max Temp implemented

* DynaTemp UI Checkbox

Trigger DynaTemp on checkbox

* DynaTemp UI checkbox edition

Hell Yeah! DynaTemp!

* Remove greedy dynatemp

* Fix race condition caused by debug print

* Fixed broken presets and miro

Fixes broken presets and mirostat

* Remove debug function + HHI temp

Also removed unnecessary softmax double precision

* Fix whitespace (?) for generate function

* epic upstream renaming scheme fix

* fix stupid indents

* Other cleanup

Reintroduce unused rep pen function, move temp functions first before entropy dynamic temp

* Slight indent fix

* revert batch pyinstaller maker to mainline

and also delete experts.txt since adjustable routing is also being removed for the PR

* compact dynatemp into a single value dynatemp_range. This is a float which represents the allowed deviation from the min and max temperature when using dynatemp. Thus, if we want a value of dynatemp_min=0.3, dynatemp_max=0.5, then we would simply set temperature=0.4 and dynatemp_range=0.1. Functionally dynatemp would operate the same, but it would simplify usage and make it a single easy to adjust value.

---------

Co-authored-by: Alexander Abushady <aabushady214@gmail.com>
Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
This commit is contained in:
kalomaze 2024-01-05 21:13:16 -06:00 • committed by GitHub
parent 427ba21e62
commit 123bff9a0f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 132 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

22
gpttype_adapter.cpp
View file

@ -482,7 +482,7 @@ void sample_grammar(FileFormat file_format, int32_t n_vocab, llama_token_data_ar
}
int SampleLogits(const float * logits, int n_ctx, int n_vocab, int rep_pen_range, float rep_pen, float presence_penalty, float top_k, float top_a, float top_p, float min_p, float typical_p, float tfs, float temp, std::mt19937 & rng,
int mirostat, float mirostat_tau, float mirostat_eta, const std::vector<samplers> & sampler_order, llama_grammar * grammar)
int mirostat, float mirostat_tau, float mirostat_eta, const std::vector<samplers> & sampler_order, llama_grammar * grammar, float dynatemp_range)
{
int id = 0;
std::vector<llama_token_data> candidates;
@ -541,7 +541,19 @@ int mirostat, float mirostat_tau, float mirostat_eta, const std::vector<samplers
llama_sample_typical(nullptr, &candidates_p, typical_p,1);
break;
case KCPP_SAMPLER_TEMP:
sample_temperature(&candidates_p, temp);
if (dynatemp_range>0)
{
float dynatemp_min = temp - dynatemp_range;
float dynatemp_max = temp + dynatemp_range;
//do not allow negative values
dynatemp_min = dynatemp_min<0?0:dynatemp_min;
dynatemp_max = dynatemp_max<0?0:dynatemp_max;
llama_sample_entropy(nullptr, &candidates_p, temp, dynatemp_min, dynatemp_max);
}
else
{
sample_temperature(&candidates_p, temp);
}
break;
case KCPP_SAMPLER_REP_PEN:
sample_rep_pen(n_ctx, rep_pen_range, rep_pen, presence_penalty, &candidates_p);
@ -1480,6 +1492,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs, generation_o
}
std::string addedmemory = inputs.memory;
kcpp_params->prompt = inputs.prompt;
kcpp_params->seed = inputs.seed;
kcpp_params->n_predict = inputs.max_length;
@ -1495,10 +1508,12 @@ generation_outputs gpttype_generate(const generation_inputs inputs, generation_o
kcpp_params->mirostat = inputs.mirostat;
kcpp_params->mirostat_eta = inputs.mirostat_eta;
kcpp_params->mirostat_tau = inputs.mirostat_tau;
kcpp_params->dynatemp_range = inputs.dynatemp_range;
kcpp_params->n_ctx = inputs.max_context_length;
kcpp_params->n_batch = n_batch;
kcpp_params->n_threads = n_threads;
kcpp_params->n_threads_batch = n_blasthreads;
bool stream_sse = inputs.stream_sse;
bool allow_regular_prints = (debugmode!=-1 && !inputs.quiet) || debugmode >= 1;
@ -1889,6 +1904,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs, generation_o
const float presence_penalty = kcpp_params->presence_penalty;
const float typical_p = kcpp_params->typical_p;
const float tfs_z = kcpp_params->tfs_z;
const float dynatemp_range = kcpp_params->dynatemp_range;
if (!startedsampling)
{
@ -1944,7 +1960,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs, generation_o
id = SampleLogits(logitsPtr, nctx, n_vocab, last_n_size, repeat_penalty, presence_penalty,
top_k, top_a, top_p, min_p, typical_p, tfs_z, temp, rng,
kcpp_params->mirostat, kcpp_params->mirostat_tau, kcpp_params->mirostat_eta, sampler_order, grammar);
kcpp_params->mirostat, kcpp_params->mirostat_tau, kcpp_params->mirostat_eta, sampler_order, grammar, dynatemp_range);
if (grammar != nullptr) {
grammar_accept_token(file_format, n_vocab, grammar, id);