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

sampling : refactor + optimize penalties sampler (#10803)

Browse source 
* sampling : refactor + optimize penalties sampler

ggml-ci

* common : apply ignore_eos as logit bias

ggml-ci

* batched : remove penalties sampler

* params : allow penalty_last_n == -1 to be equal to context size

ggml-ci

* common : by default, move the penalties at the end of the sampling chain

ggml-ci

* common : ignore all EOG tokens

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* common : move back the penalties at the front of the sampling chain

ggml-ci

* readme : restore hint about --ignore-eos flag [no ci]

* llama : minor

ggml-ci

* webui : update

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-12-16 12:31:14 +02:00 • committed by GitHub
parent 4ddd199f6f
commit 644fd71b44
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 111 additions and 152 deletions
Download patch file Download diff file Expand all files Collapse all files

5
examples/server/README.md
View file

@ -104,7 +104,6 @@ The project is under active development, and we are [looking for feedback and co
| `-s, --seed SEED` | RNG seed (default: -1, use random seed for -1) |
| `--sampling-seq SEQUENCE` | simplified sequence for samplers that will be used (default: dkypmxt) |
| `--ignore-eos` | ignore end of stream token and continue generating (implies --logit-bias EOS-inf) |
| `--penalize-nl` | penalize newline tokens (default: false) |
| `--temp N` | temperature (default: 0.8) |
| `--top-k N` | top-k sampling (default: 40, 0 = disabled) |
| `--top-p N` | top-p sampling (default: 0.9, 1.0 = disabled) |
@ -393,8 +392,6 @@ These words will not be included in the completion, so make sure to add them to
`repeat_last_n`: Last n tokens to consider for penalizing repetition. Default: `64`, where `0` is disabled and `-1` is ctx-size.
`penalize_nl`: Penalize newline tokens when applying the repeat penalty. Default: `true`
`presence_penalty`: Repeat alpha presence penalty. Default: `0.0`, which is disabled.
`frequency_penalty`: Repeat alpha frequency penalty. Default: `0.0`, which is disabled.
@ -655,7 +652,6 @@ This endpoint is public (no API key check). By default, it is read-only. To make
"mirostat": 0,
"mirostat_tau": 5.0,
"mirostat_eta": 0.10000000149011612,
"penalize_nl": false,
"stop": [],
"max_tokens": -1,
"n_keep": 0,
@ -845,7 +841,6 @@ Example:
"mirostat": 0,
"mirostat_tau": 5.0,
"mirostat_eta": 0.10000000149011612,
"penalize_nl": false,
"stop": [],
"max_tokens": -1,
"n_keep": 0,

BIN
examples/server/public/index.html.gz
View file

Binary file not shown.

1
examples/server/public_legacy/index-new.html
View file

@ -39,7 +39,6 @@
temperature: 0.8, // adapt all following parameters to optimized min-p requierements. If for non-english, set to 0.6 or lower
repeat_last_n: 0, // 0 = disable penalty, -1 = context size
repeat_penalty: 1.0, // 1.0 = disabled
penalize_nl: false, // true only useful for infinite completion
dry_multiplier: 0.0, // 0.0 = disabled, 0.8 works well
dry_base: 1.75, // 0.0 = disabled
dry_allowed_length: 2, // tokens extending repetitions beyond this receive penalty, 2 works well

2
examples/server/public_legacy/index.html
View file

@ -303,7 +303,6 @@
temperature: 0.7,
repeat_last_n: 256, // 0 = disable penalty, -1 = context size
repeat_penalty: 1.18, // 1.0 = disabled
penalize_nl: false,
dry_multiplier: 0.0, // 0.0 = disabled, 0.8 works well
dry_base: 1.75, // 0.0 = disabled
dry_allowed_length: 2, // tokens extending repetitions beyond this receive penalty, 2 works well
@ -1006,7 +1005,6 @@
${FloatField({ label: "Temperature", max: 2.0, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature })}
${FloatField({ label: "Penalize repeat sequence", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty })}
${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
${BoolField({ label: "Penalize repetition of newlines", name: "penalize_nl", value: params.value.penalize_nl })}
${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: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}

28
examples/server/server.cpp
View file

@ -135,7 +135,6 @@ struct slot_params {
{"mirostat", sampling.mirostat},
{"mirostat_tau", sampling.mirostat_tau},
{"mirostat_eta", sampling.mirostat_eta},
{"penalize_nl", sampling.penalize_nl},
{"stop", antiprompt},
{"max_tokens", n_predict}, // User configured n_predict
{"n_keep", n_keep},
@ -184,6 +183,7 @@ struct server_task {
static slot_params params_from_json_cmpl(
const llama_model * model,
const llama_context * ctx,
const common_params & params_base,
const json & data) {
slot_params params;
@ -226,7 +226,6 @@ struct server_task {
params.sampling.mirostat = json_value(data, "mirostat", defaults.sampling.mirostat);
params.sampling.mirostat_tau = json_value(data, "mirostat_tau", defaults.sampling.mirostat_tau);
params.sampling.mirostat_eta = json_value(data, "mirostat_eta", defaults.sampling.mirostat_eta);
params.sampling.penalize_nl = json_value(data, "penalize_nl", defaults.sampling.penalize_nl);
params.sampling.seed = json_value(data, "seed", defaults.sampling.seed);
params.sampling.n_probs = json_value(data, "n_probs", defaults.sampling.n_probs);
params.sampling.min_keep = json_value(data, "min_keep", defaults.sampling.min_keep);
@ -239,8 +238,27 @@ struct server_task {
params.speculative.n_min = std::max(params.speculative.n_min, 2);
params.speculative.n_max = std::max(params.speculative.n_max, 0);
// TODO: add more sanity checks for the input parameters
if (params.sampling.penalty_last_n < -1) {
throw std::runtime_error("Error: repeat_last_n must be >= -1");
}
if (params.sampling.dry_penalty_last_n < -1) {
throw std::runtime_error("Error: dry_penalty_last_n must be >= -1");
}
if (params.sampling.penalty_last_n == -1) {
// note: should be the slot's context and not the full context, but it's ok
params.sampling.penalty_last_n = llama_n_ctx(ctx);
}
if (params.sampling.dry_penalty_last_n == -1) {
params.sampling.dry_penalty_last_n = llama_n_ctx(ctx);
}
if (params.sampling.dry_base < 1.0f) {
params.sampling.dry_base = defaults.sampling.dry_base;
params.sampling.dry_base = defaults.sampling.dry_base;
}
// sequence breakers for DRY
@ -1469,7 +1487,7 @@ struct server_context {
n_ctx = llama_n_ctx(ctx);
add_bos_token = llama_add_bos_token(model);
has_eos_token = !llama_add_eos_token(model);
has_eos_token = llama_token_eos(model) != LLAMA_TOKEN_NULL;
if (!params_base.speculative.model.empty()) {
SRV_INF("loading draft model '%s'\n", params_base.speculative.model.c_str());
@ -3381,7 +3399,7 @@ int main(int argc, char ** argv) {
task.index = i;
task.prompt_tokens = std::move(tokenized_prompts[i]);
task.params = server_task::params_from_json_cmpl(ctx_server.model, ctx_server.params_base, data);
task.params = server_task::params_from_json_cmpl(ctx_server.model, ctx_server.ctx, ctx_server.params_base, data);
task.id_selected_slot = json_value(data, "id_slot", -1);
// OAI-compat

2
examples/server/themes/buttons-top/index.html
View file

@ -222,7 +222,6 @@
temperature: 0.7,
repeat_last_n: 256, // 0 = disable penalty, -1 = context size
repeat_penalty: 1.18, // 1.0 = disabled
penalize_nl: false,
top_k: 40, // <= 0 to use vocab size
top_p: 0.95, // 1.0 = disabled
min_p: 0.05, // 0 = disabled
@ -779,7 +778,6 @@
${FloatField({ label: "Temperature", max: 2.0, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature })}
${FloatField({ label: "Penalize repeat sequence", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty })}
${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
${BoolField({ label: "Penalize repetition of newlines", name: "penalize_nl", value: params.value.penalize_nl })}
${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: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}

2
examples/server/themes/wild/index.html
View file

@ -225,7 +225,6 @@
temperature: 0.7,
repeat_last_n: 256, // 0 = disable penalty, -1 = context size
repeat_penalty: 1.18, // 1.0 = disabled
penalize_nl: false,
top_k: 40, // <= 0 to use vocab size
top_p: 0.95, // 1.0 = disabled
min_p: 0.05, // 0 = disabled
@ -782,7 +781,6 @@
${FloatField({ label: "Temperature", max: 2.0, min: 0.0, name: "temperature", step: 0.01, value: params.value.temperature })}
${FloatField({ label: "Penalize repeat sequence", max: 2.0, min: 0.0, name: "repeat_penalty", step: 0.01, value: params.value.repeat_penalty })}
${IntField({ label: "Consider N tokens for penalize", max: 2048, min: 0, name: "repeat_last_n", value: params.value.repeat_last_n })}
${BoolField({ label: "Penalize repetition of newlines", name: "penalize_nl", value: params.value.penalize_nl })}
${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: "Min-P sampling", max: 1.0, min: 0.0, name: "min_p", step: 0.01, value: params.value.min_p })}

2
examples/server/webui/src/main.js
View file

@ -33,7 +33,7 @@ const CONFIG_DEFAULT = {
systemMessage: 'You are a helpful assistant.',
showTokensPerSecond: false,
// make sure these default values are in sync with `common.h`
samplers: 'dkypmxt',
samplers: 'edkypmxt',
temperature: 0.8,
dynatemp_range: 0.0,
dynatemp_exponent: 1.0,