sampling : refactor init to use llama_sampling_params (#3696)

* sampling : refactor init to use llama_sampling_params

* llama : combine repetition, frequency and presence penalties in 1 call

* examples : remove embd-input and gptneox-wip

* sampling : rename penalty params + reduce size of "prev" vector

* sampling : add llama_sampling_print helper

* sampling : hide prev behind API and apply #3661

ggml-ci

1 files changed, 5 insertions, 11 deletions

diff --git a/llama.h b/llama.h
index 51010e03..306f5b38 100644
--- a/llama.h
+++ b/llama.h
@@ -560,21 +560,15 @@ extern "C" {
     LLAMA_API void llama_set_rng_seed(struct llama_context * ctx, uint32_t seed);
 
     /// @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix.
-    LLAMA_API void llama_sample_repetition_penalty(
-            struct llama_context * ctx,
-          llama_token_data_array * candidates,
-               const llama_token * last_tokens,
-                          size_t   last_tokens_size,
-                          float    penalty);
-
     /// @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details.
-    LLAMA_API void llama_sample_frequency_and_presence_penalties(
+    LLAMA_API void llama_sample_repetition_penalties(
             struct llama_context * ctx,
           llama_token_data_array * candidates,
                const llama_token * last_tokens,
-                          size_t   last_tokens_size,
-                           float   alpha_frequency,
-                           float   alpha_presence);
+                          size_t   penalty_last_n,
+                           float   penalty_repeat,
+                           float   penalty_freq,
+                           float   penalty_present);
 
     /// @details Apply classifier-free guidance to the logits as described in academic paper "Stay on topic with Classifier-Free Guidance" https://arxiv.org/abs/2306.17806
     /// @param candidates A vector of `llama_token_data` containing the candidate tokens, the logits must be directly extracted from the original generation context without being sorted.