Merge Dynamic Temp UI + cleanups into dynatemp-pr-upstream

Author: kalomaze

common/common.h

@@ -80,6 +80,12 @@ struct gpt_params {
     int32_t mirostat          = 0;     // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
     float   mirostat_tau      = 5.00f; // target entropy
     float   mirostat_eta      = 0.10f; // learning rate
+
+    // DynaTemp!
+    bool    dynatemp           = false; // enable DynaTemp
+    float   min_temp           = 0.00f; // minimum temperature
+    float   max_temp           = 2.00f; // maximum temperature
+
     // // sampling parameters
     struct llama_sampling_params sparams;
 

common/sampling.h

@@ -25,6 +25,9 @@ typedef struct llama_sampling_params {
     int32_t     mirostat              = 0;        // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
     float       mirostat_tau          = 5.00f;    // target entropy
     float       mirostat_eta          = 0.10f;    // learning rate
+    bool        dynatemp              = false;    // dynamic temperature
+    float       min_temp              = 0.00f; // minimum temperature
+    float       max_temp              = 2.00f; // maximum temperature
     bool        penalize_nl           = true;     // consider newlines as a repeatable token
     std::string samplers_sequence     = "kfypmt"; // top_k, tail_free, typical_p, top_p, min_p, temp
 

expose.h

@@ -81,7 +81,11 @@ struct generation_inputs
     const char * grammar;
     const bool grammar_retain_state;
     const bool quiet = false;
+    const bool dynatemp = false;
+    const float min_temp;
+    const float max_temp;
     const logit_bias logit_biases[logit_bias_max];
+
 };
 struct generation_outputs
 {

gpttype_adapter.cpp

@@ -481,7 +481,7 @@ 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, bool dynatemp, float min_temp, float max_temp)
 {
     int id = 0;
     std::vector<llama_token_data> candidates;
@@ -540,7 +540,14 @@ 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)
+                    {
+                        llama_sample_entropy(nullptr, &candidates_p, temp, min_temp, max_temp);
+                    }
+                    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);
@@ -1479,6 +1486,7 @@ 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;
@@ -1494,10 +1502,14 @@ 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 = inputs.dynatemp;
+    kcpp_params->min_temp = inputs.min_temp;
+    kcpp_params->max_temp = inputs.max_temp;
     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;
@@ -1888,6 +1900,9 @@ 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 = kcpp_params->dynatemp;
+            const float min_temp = kcpp_params->min_temp;
+            const float max_temp = kcpp_params->max_temp;
 
             if (!startedsampling)
             {
@@ -1943,7 +1958,7 @@ 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, min_temp, max_temp);
 
             if (grammar != nullptr) {
                 grammar_accept_token(file_format, n_vocab, grammar, id);

kcpp_docs.embd

@@ -139,6 +139,21 @@
                            "description": "If true, prevents the EOS token from being generated (Ban EOS). For unbantokens, set this to false.",
                            "type": "boolean"
                         },
+                        "dynatemp": {
+                           "default": false,
+                           "description": "If true, uses dynamic temperature. If false, uses static temperature.",
+                           "type": "boolean"
+                        },
+                        "min_temp": {
+                           "description": "Dynatemp Minimum temperature value.",
+                           "exclusiveMinimum": 0,
+                           "type": "number"
+                        },
+                        "max_temp": {
+                           "description": "Maximum temperature value.",
+                           "exclusiveMinimum": 0,
+                           "type": "number"
+                        },
                         "mirostat": {
                            "description": "KoboldCpp ONLY. Sets the mirostat mode, 0=disabled, 1=mirostat_v1, 2=mirostat_v2",
                            "minimum": 0,
@@ -876,4 +891,4 @@
 
 </body>
 
-</html>
+</html>