parallel : add option to load external prompt file (#3416)

* Enable external file and add datestamp

* Add name of external file at end

* Upload ToK2024

* Delete ToK2024.txt

* Experiments with jeopardy

* Move ParallelQuestions to /proimpts and rename

* Interim commit

* Interim commit

* Final revision

* Remove trailing whitespace

* remove cmake_all.sh

* Remove cmake_all.sh

* Changed .gitignore

* Improved reporting and new question files.

* Corrected typo

* More LLM questions

* Update LLM-questions.txt

* Yet more LLM-questions

* Remove jeopardy results file

* Reinstate original jeopardy.sh

* Update examples/parallel/parallel.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

.github/workflows/build.yml

@@ -10,10 +10,10 @@ on:
   push:
     branches:
       - master
-    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu']
+    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift']
   pull_request:
     types: [opened, synchronize, reopened]
-    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu']
+    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift']
 
 env:
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
@@ -258,7 +258,7 @@ jobs:
 
     strategy:
       matrix:
-        destination: ['platform=macOS,name=Any Mac', 'platform=iOS,name=Any iOS Device', 'platform=tvOS,name=Any tvOS Device']
+        destination: ['generic/platform=macOS', 'generic/platform=iOS', 'generic/platform=tvOS']
 
     steps:
       - name: Clone

common/common.cpp

@@ -167,6 +167,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 invalid_param = true;
                 break;
             }
+            // store the external file name in params
+            params.prompt_file = argv[i];
             std::copy(std::istreambuf_iterator<char>(file), std::istreambuf_iterator<char>(), back_inserter(params.prompt));
             if (params.prompt.back() == '\n') {
                 params.prompt.pop_back();
@@ -361,7 +363,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 invalid_param = true;
                 break;
             }
-            params.lora_adapter.push_back({argv[i], 1.0f});
+            params.lora_adapter.push_back(std::make_tuple(argv[i], 1.0f));
             params.use_mmap = false;
         } else if (arg == "--lora-scaled") {
             if (++i >= argc) {
@@ -373,7 +375,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 invalid_param = true;
                 break;
             }
-            params.lora_adapter.push_back({lora_adapter, std::stof(argv[i])});
+            params.lora_adapter.push_back(std::make_tuple(lora_adapter, std::stof(argv[i])));
             params.use_mmap = false;
         } else if (arg == "--lora-base") {
             if (++i >= argc) {
@@ -1020,10 +1022,11 @@ llama_token llama_sample_token(
             id = llama_sample_token_mirostat_v2(ctx, &cur_p, mirostat_tau, mirostat_eta, &mirostat_mu);
         } else {
             // Temperature sampling
-            llama_sample_top_k      (ctx, &cur_p, top_k, 1);
-            llama_sample_tail_free  (ctx, &cur_p, tfs_z, 1);
-            llama_sample_typical    (ctx, &cur_p, typical_p, 1);
-            llama_sample_top_p      (ctx, &cur_p, top_p, 1);
+            size_t min_keep = std::max(1, params.n_probs);
+            llama_sample_top_k      (ctx, &cur_p, top_k, min_keep);
+            llama_sample_tail_free  (ctx, &cur_p, tfs_z, min_keep);
+            llama_sample_typical    (ctx, &cur_p, typical_p, min_keep);
+            llama_sample_top_p      (ctx, &cur_p, top_p, min_keep);
             llama_sample_temp(ctx, &cur_p, temp);
 
             {

common/common.h

@@ -79,6 +79,7 @@ struct gpt_params {
     std::string model_draft       = "";                              // draft model for speculative decoding
     std::string model_alias       = "unknown"; // model alias
     std::string prompt            = "";
+    std::string prompt_file       = "";  // store the external prompt file name
     std::string path_prompt_cache = "";  // path to file for saving/loading prompt eval state
     std::string input_prefix      = "";  // string to prefix user inputs with
     std::string input_suffix      = "";  // string to suffix user inputs with

convert-falcon-hf-to-gguf.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import argparse
+import contextlib
 import json
 import os
 import struct
@@ -20,10 +21,10 @@ if 'NO_LOCAL_GGUF' not in os.environ:
 import gguf
 
 
-def count_model_parts(dir_model: Path) -> int:
+def count_model_parts(dir_model: Path, prefix: str) -> int:
     num_parts = 0
     for filename in os.listdir(dir_model):
-        if filename.startswith("pytorch_model-"):
+        if filename.startswith(prefix):
             num_parts += 1
 
     if num_parts > 0:
@@ -77,20 +78,26 @@ print("gguf: loading model "+dir_model.name)
 with open(dir_model / "config.json", "r", encoding="utf-8") as f:
     hparams = json.load(f)
 
-if hparams["architectures"][0] != "RWForCausalLM":
+if hparams["architectures"][0] != "FalconForCausalLM":
     print("Model architecture not supported: " + hparams["architectures"][0])
 
     sys.exit(1)
 
 # get number of model parts
-num_parts = count_model_parts(dir_model)
+num_parts = count_model_parts(dir_model, "model-00")
+if num_parts:
+    is_safetensors = True
+    from safetensors import safe_open
+else:
+    is_safetensors = False
+    num_parts = count_model_parts(dir_model, "pytorch_model-")
 
 ARCH=gguf.MODEL_ARCH.FALCON
 gguf_writer = gguf.GGUFWriter(fname_out, gguf.MODEL_ARCH_NAMES[ARCH])
 
 print("gguf: get model metadata")
 
-block_count = hparams["n_layer"]
+block_count = hparams["num_hidden_layers"]
 
 gguf_writer.add_name("Falcon")
 gguf_writer.add_context_length(2048) # not in config.json
@@ -98,9 +105,9 @@ gguf_writer.add_tensor_data_layout("jploski") # qkv tensor transform
 gguf_writer.add_embedding_length(hparams["hidden_size"])
 gguf_writer.add_feed_forward_length(4 * hparams["hidden_size"])
 gguf_writer.add_block_count(block_count)
-gguf_writer.add_head_count(hparams["n_head"])
-if "n_head_kv" in hparams:
-    gguf_writer.add_head_count_kv(hparams["n_head_kv"])
+gguf_writer.add_head_count(hparams["num_attention_heads"])
+if "num_kv_heads" in hparams:
+    gguf_writer.add_head_count_kv(hparams["num_kv_heads"])
 else:
     gguf_writer.add_head_count_kv(1)
 gguf_writer.add_layer_norm_eps(hparams["layer_norm_epsilon"])
@@ -146,8 +153,8 @@ special_vocab.add_to_gguf(gguf_writer)
 tensor_map = gguf.get_tensor_name_map(ARCH,block_count)
 
 # params for qkv transform
-n_head    = hparams["n_head"]
-n_head_kv = hparams["n_head_kv"] if "n_head_kv" in hparams else 1
+n_head    = hparams["num_attention_heads"]
+n_head_kv = hparams["num_kv_heads"] if "num_kv_heads" in hparams else 1
 
 head_dim = hparams["hidden_size"] // n_head
 
@@ -156,6 +163,10 @@ print("gguf: get tensor metadata")
 
 if num_parts == 0:
     part_names = iter(("pytorch_model.bin",))
+elif is_safetensors:
+    part_names = (
+        f"model-{n:05}-of-{num_parts:05}.safetensors" for n in range(1, num_parts + 1)
+    )
 else:
     part_names = (
         f"pytorch_model-{n:05}-of-{num_parts:05}.bin" for n in range(1, num_parts + 1)
@@ -165,60 +176,64 @@ for part_name in part_names:
     if args.vocab_only:
         break
     print("gguf: loading model part '" + part_name + "'")
-    model_part = torch.load(dir_model / part_name, map_location="cpu")
+    if is_safetensors:
+        ctx = safe_open(dir_model / part_name, framework="pt", device="cpu")
+    else:
+        ctx = contextlib.nullcontext(torch.load(dir_model / part_name, map_location="cpu"))
 
-    for name in model_part.keys():
-        data = model_part[name]
+    with ctx as model_part:
+        for name in model_part.keys():
+            data = model_part.get_tensor(name) if is_safetensors else model_part[name]
 
-        old_dtype = data.dtype
+            old_dtype = data.dtype
 
-        # convert any unsupported data types to float32
-        if data.dtype != torch.float16 and data.dtype != torch.float32:
-            data = data.to(torch.float32)
+            # convert any unsupported data types to float32
+            if data.dtype != torch.float16 and data.dtype != torch.float32:
+                data = data.to(torch.float32)
 
-        # QKV tensor transform
-        # The original query_key_value tensor contains n_head_kv "kv groups",
-        # each consisting of n_head/n_head_kv query weights followed by one key
-        # and one value weight (shared by all query heads in the kv group).
-        # This layout makes it a big pain to work with in GGML.
-        # So we rearrange them here,, so that we have n_head query weights
-        # followed by n_head_kv key weights followed by n_head_kv value weights,
-        # in contiguous fashion.
-        # ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert-hf-to-ggml.py
+            # QKV tensor transform
+            # The original query_key_value tensor contains n_head_kv "kv groups",
+            # each consisting of n_head/n_head_kv query weights followed by one key
+            # and one value weight (shared by all query heads in the kv group).
+            # This layout makes it a big pain to work with in GGML.
+            # So we rearrange them here,, so that we have n_head query weights
+            # followed by n_head_kv key weights followed by n_head_kv value weights,
+            # in contiguous fashion.
+            # ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert-hf-to-ggml.py
 
-        if "query_key_value" in name:
-            qkv = data.view(n_head_kv, n_head // n_head_kv + 2, head_dim, head_dim * n_head)
-            q = qkv[:, :-2 ].reshape(n_head * head_dim, head_dim * n_head)
-            k = qkv[:, [-2]].reshape(n_head_kv * head_dim, head_dim * n_head)
-            v = qkv[:, [-1]].reshape(n_head_kv * head_dim, head_dim * n_head)
-            data = torch.cat((q,k,v)).reshape_as(data)
+            if "query_key_value" in name:
+                qkv = data.view(n_head_kv, n_head // n_head_kv + 2, head_dim, head_dim * n_head)
+                q = qkv[:, :-2 ].reshape(n_head * head_dim, head_dim * n_head)
+                k = qkv[:, [-2]].reshape(n_head_kv * head_dim, head_dim * n_head)
+                v = qkv[:, [-1]].reshape(n_head_kv * head_dim, head_dim * n_head)
+                data = torch.cat((q,k,v)).reshape_as(data)
 
-        data = data.squeeze().numpy()
+            data = data.squeeze().numpy()
 
-        # map tensor names
-        new_name = tensor_map.get_name(name, try_suffixes = (".weight", ".bias"))
-        if new_name is None:
-            print("Can not map tensor '" + name + "'")
-            sys.exit()
+            # map tensor names
+            new_name = tensor_map.get_name(name, try_suffixes = (".weight", ".bias"))
+            if new_name is None:
+                print("Can not map tensor '" + name + "'")
+                sys.exit()
 
-        n_dims = len(data.shape)
-        data_dtype = data.dtype
+            n_dims = len(data.shape)
+            data_dtype = data.dtype
 
-        # if f32 desired, convert any float16 to float32
-        if ftype == 0 and data_dtype == np.float16:
-            data = data.astype(np.float32)
+            # if f32 desired, convert any float16 to float32
+            if ftype == 0 and data_dtype == np.float16:
+                data = data.astype(np.float32)
 
-        # TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32
-        if ftype == 1 and data_dtype == np.float16 and n_dims == 1:
-            data = data.astype(np.float32)
+            # TODO: Why cant we use these float16 as-is? There should be not reason to store float16 as float32
+            if ftype == 1 and data_dtype == np.float16 and n_dims == 1:
+                data = data.astype(np.float32)
 
-        # if f16 desired, convert any float32 2-dim weight tensors to float16
-        if ftype == 1 and data_dtype == np.float32 and name.endswith(".weight") and n_dims == 2:
-            data = data.astype(np.float16)
+            # if f16 desired, convert any float32 2-dim weight tensors to float16
+            if ftype == 1 and data_dtype == np.float32 and name.endswith(".weight") and n_dims == 2:
+                data = data.astype(np.float16)
 
-        print(new_name + ", n_dims = " + str(n_dims) + ", " + str(old_dtype) + " --> " + str(data.dtype))
+            print(new_name + ", n_dims = " + str(n_dims) + ", " + str(old_dtype) + " --> " + str(data.dtype))
 
-        gguf_writer.add_tensor(new_name, data)
+            gguf_writer.add_tensor(new_name, data)
 
 
 print("gguf: write header")

examples/jeopardy/README.md

@@ -2,7 +2,7 @@
 
 This is pretty much just a straight port of aigoopy/llm-jeopardy/ with an added graph viewer.
 
-The jeopardy test can be used to compare the fact knowledge of different models and compare them to eachother. This is in contrast to some other tests, which test logical deduction, creativity, writing skills, etc.
+The jeopardy test can be used to compare the fact knowledge of different models and compare them to each other. This is in contrast to some other tests, which test logical deduction, creativity, writing skills, etc.
 
 
 Step 1: Open jeopardy.sh and modify the following:

examples/parallel/parallel.cpp

@@ -10,6 +10,7 @@
 #include <cstdio>
 #include <string>
 #include <vector>
+#include <ctime>
 
 // trim whitespace from the beginning and end of a string
 static std::string trim(const std::string & str) {
@@ -70,6 +71,26 @@ struct client {
     std::vector<llama_token> tokens_prev;
 };
 
+static void print_date_time() {
+    std::time_t current_time = std::time(nullptr);
+    std::tm* local_time = std::localtime(&current_time);
+    char buffer[80];
+    strftime(buffer, sizeof(buffer), "%Y-%m-%d %H:%M:%S", local_time);
+
+    printf("\n\033[35mrun parameters as at %s\033[0m\n", buffer);
+}
+
+// Define a split string function to ...
+static std::vector<std::string> split_string(const std::string& input, char delimiter) {
+    std::vector<std::string> tokens;
+    std::istringstream stream(input);
+    std::string token;
+    while (std::getline(stream, token, delimiter)) {
+        tokens.push_back(token);
+    }
+    return tokens;
+}
+
 int main(int argc, char ** argv) {
     srand(1234);
 
@@ -104,6 +125,23 @@ int main(int argc, char ** argv) {
     params.logits_all = true;
     std::tie(model, ctx) = llama_init_from_gpt_params(params);
 
+    // load the prompts from an external file if there are any
+    if (params.prompt.empty()) {
+        printf("\n\033[32mNo new questions so proceed with build-in defaults.\033[0m\n");
+    } else {
+        // Output each line of the input params.prompts vector and copy to k_prompts
+        int index = 0;
+        printf("\n\033[32mNow printing the external prompt file %s\033[0m\n\n", params.prompt_file.c_str());
+
+        std::vector<std::string> prompts = split_string(params.prompt, '\n');
+        for (const auto& prompt : prompts) {
+            k_prompts.resize(index + 1);
+            k_prompts[index] = prompt;
+            index++;
+            printf("%3d prompt: %s\n", index, prompt.c_str());
+        }
+    }
+
     fprintf(stderr, "\n\n");
     fflush(stderr);
 
@@ -233,7 +271,7 @@ int main(int argc, char ** argv) {
                     client.n_decoded = 0;
                     client.i_batch   = batch.n_tokens - 1;
 
-                    LOG_TEE("\033[1mClient %3d, seq %4d, started decoding ...\033[0m\n", client.id, client.seq_id);
+                    LOG_TEE("\033[31mClient %3d, seq %4d, started decoding ...\033[0m\n", client.id, client.seq_id);
 
                     g_seq_id += 1;
 
@@ -336,8 +374,8 @@ int main(int argc, char ** argv) {
 
                     const auto t_main_end = ggml_time_us();
 
-                    LOG_TEE("\033[1mClient %3d, seq %4d, prompt %4d t, response %4d t, time %5.2f s, speed %5.2f t/s, cache miss %d \033[0m \n\nInput:    %s\nResponse: %s\n\n",
-                            client.id, client.seq_id, client.n_prompt, client.n_decoded,
+                    LOG_TEE("\033[31mClient %3d, seq %3d/%3d, prompt %4d t, response %4d t, time %5.2f s, speed %5.2f t/s, cache miss %d \033[0m \nInput:    %s\n\033[35mResponse: %s\033[0m\n\n",
+                            client.id, client.seq_id, n_seq, client.n_prompt, client.n_decoded,
                             (t_main_end - client.t_start_prompt) / 1e6,
                             (double) (client.n_prompt + client.n_decoded) / (t_main_end - client.t_start_prompt) * 1e6,
                             n_cache_miss,
@@ -357,13 +395,21 @@ int main(int argc, char ** argv) {
 
     const auto t_main_end = ggml_time_us();
 
-    LOG_TEE("\n\n");
+    print_date_time();
+
+    LOG_TEE("\n%s: n_parallel = %d, n_sequences = %d, cont_batching = %d, system tokens = %d\n", __func__, n_clients, n_seq, cont_batching, n_tokens_system);
+    if (params.prompt_file.empty()) {
+        params.prompt_file = "used built-in defaults";
+    }
+    LOG_TEE("External prompt file: \033[32m%s\033[0m\n", params.prompt_file.c_str());
+    LOG_TEE("Model and path used:  \033[32m%s\033[0m\n\n", params.model.c_str());
+
     LOG_TEE("Total prompt tokens: %6d, speed: %5.2f t/s\n", n_total_prompt, (double) (n_total_prompt              ) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Total gen tokens:    %6d, speed: %5.2f t/s\n", n_total_gen,    (double) (n_total_gen                 ) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Total speed (AVG):   %6s  speed: %5.2f t/s\n", "",             (double) (n_total_prompt + n_total_gen) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Cache misses:        %6d\n", n_cache_miss);
 
-    LOG_TEE("\n\n");
+    LOG_TEE("\n");
 
     llama_print_timings(ctx);
 

examples/server/server.cpp

@@ -534,98 +534,20 @@ struct llama_server_context
             return result;
         }
 
-        // out of user input, sample next token
-        const float temp = params.temp;
-        const int32_t top_k = params.top_k <= 0 ? llama_n_vocab(model) : params.top_k;
-        const float top_p = params.top_p;
-        const float tfs_z = params.tfs_z;
-        const float typical_p = params.typical_p;
-        const int32_t repeat_last_n = params.repeat_last_n < 0 ? n_ctx : params.repeat_last_n;
-        const float repeat_penalty = params.repeat_penalty;
-        const float alpha_presence = params.presence_penalty;
-        const float alpha_frequency = params.frequency_penalty;
-        const int mirostat = params.mirostat;
-        const float mirostat_tau = params.mirostat_tau;
-        const float mirostat_eta = params.mirostat_eta;
-        const bool penalize_nl = params.penalize_nl;
-        const int32_t n_probs = params.n_probs;
-
         {
-            auto *logits = llama_get_logits(ctx);
-            auto n_vocab = llama_n_vocab(model);
-
-            // Apply params.logit_bias map
-            for (const auto &it : params.logit_bias)
-            {
-                logits[it.first] += it.second;
-            }
-
+            // out of user input, sample next token
             std::vector<llama_token_data> candidates;
-            candidates.reserve(n_vocab);
-            for (llama_token token_id = 0; token_id < n_vocab; token_id++)
+            candidates.reserve(llama_n_vocab(model));
+
+            result.tok = llama_sample_token(ctx, NULL, grammar, params, last_n_tokens, candidates);
+
+            llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
+
+            const int32_t n_probs = params.n_probs;
+            if (params.temp <= 0 && n_probs > 0)
             {
-                candidates.emplace_back(llama_token_data{token_id, logits[token_id], 0.0f});
-            }
-
-            llama_token_data_array candidates_p = {candidates.data(), candidates.size(), false};
-
-            // Apply penalties
-            float nl_logit = logits[llama_token_nl(ctx)];
-            auto last_n_repeat = std::min(std::min((int)last_n_tokens.size(), repeat_last_n), n_ctx);
-            llama_sample_repetition_penalty(ctx, &candidates_p,
-                                            last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
-                                            last_n_repeat, repeat_penalty);
-            llama_sample_frequency_and_presence_penalties(ctx, &candidates_p,
-                                                          last_n_tokens.data() + last_n_tokens.size() - last_n_repeat,
-                                                          last_n_repeat, alpha_frequency, alpha_presence);
-            if (!penalize_nl)
-            {
-                logits[llama_token_nl(ctx)] = nl_logit;
-            }
-
-            if (grammar != nullptr) {
-                llama_sample_grammar(ctx, &candidates_p, grammar);
-            }
-
-            if (temp <= 0)
-            {
-                // Greedy sampling
-                result.tok = llama_sample_token_greedy(ctx, &candidates_p);
-                if (n_probs > 0)
-                {
-                    llama_sample_softmax(ctx, &candidates_p);
-                }
-            }
-            else
-            {
-                if (mirostat == 1)
-                {
-                    static float mirostat_mu = 2.0f * mirostat_tau;
-                    const int mirostat_m = 100;
-                    llama_sample_temp(ctx, &candidates_p, temp);
-                    result.tok = llama_sample_token_mirostat(ctx, &candidates_p, mirostat_tau, mirostat_eta, mirostat_m, &mirostat_mu);
-                }
-                else if (mirostat == 2)
-                {
-                    static float mirostat_mu = 2.0f * mirostat_tau;
-                    llama_sample_temp(ctx, &candidates_p, temp);
-                    result.tok = llama_sample_token_mirostat_v2(ctx, &candidates_p, mirostat_tau, mirostat_eta, &mirostat_mu);
-                }
-                else
-                {
-                    // Temperature sampling
-                    size_t min_keep = std::max(1, n_probs);
-                    llama_sample_top_k(ctx, &candidates_p, top_k, min_keep);
-                    llama_sample_tail_free(ctx, &candidates_p, tfs_z, min_keep);
-                    llama_sample_typical(ctx, &candidates_p, typical_p, min_keep);
-                    llama_sample_top_p(ctx, &candidates_p, top_p, min_keep);
-                    llama_sample_temp(ctx, &candidates_p, temp);
-                    result.tok = llama_sample_token(ctx, &candidates_p);
-                }
-            }
-
-            if (grammar != nullptr) {
-                llama_grammar_accept_token(ctx, grammar, result.tok);
+                // For llama_sample_token_greedy we need to sort candidates
+                llama_sample_softmax(ctx, &candidates_p);
             }
 
             for (size_t i = 0; i < std::min(candidates_p.size, (size_t)n_probs); ++i)
@@ -1015,7 +937,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
                 invalid_param = true;
                 break;
             }
-            params.lora_adapter.push_back({argv[i], 1.0f});
+            params.lora_adapter.push_back(std::make_tuple(argv[i], 1.0f));
             params.use_mmap = false;
         }
         else if (arg == "--lora-scaled")
@@ -1031,7 +953,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
                 invalid_param = true;
                 break;
             }
-            params.lora_adapter.push_back({lora_adapter, std::stof(argv[i])});
+            params.lora_adapter.push_back(std::make_tuple(lora_adapter, std::stof(argv[i])));
             params.use_mmap = false;
         }
         else if (arg == "--lora-base")

llama.cpp

@@ -125,6 +125,27 @@ static void replace_all(std::string & s, const std::string & search, const std::
     }
     s = std::move(result);
 }
+
+static bool is_float_close(float a, float b, float abs_tol) {
+    // Check for non-negative tolerance
+    if (abs_tol < 0.0) {
+        throw std::invalid_argument("Tolerance must be non-negative");
+    }
+
+    // Exact equality check
+    if (a == b) {
+        return true;
+    }
+
+    // Check for infinities
+    if (std::isinf(a) || std::isinf(b)) {
+        return false;
+    }
+
+    // Regular comparison using the provided absolute tolerance
+    return std::fabs(b - a) <= abs_tol;
+}
+
 #ifdef GGML_USE_CPU_HBM
 #include <hbwmalloc.h>
 #endif
@@ -969,7 +990,24 @@ struct llama_hparams {
     float rope_freq_scale_train;
 
     bool operator!=(const llama_hparams & other) const {
-        return static_cast<bool>(memcmp(this, &other, sizeof(llama_hparams))); // NOLINT
+        if (this->vocab_only != other.vocab_only) return true;
+        if (this->n_vocab != other.n_vocab) return true;
+        if (this->n_ctx_train != other.n_ctx_train) return true;
+        if (this->n_embd != other.n_embd) return true;
+        if (this->n_head != other.n_head) return true;
+        if (this->n_head_kv != other.n_head_kv) return true;
+        if (this->n_layer != other.n_layer) return true;
+        if (this->n_rot != other.n_rot) return true;
+        if (this->n_ff != other.n_ff) return true;
+
+        const float EPSILON = 1e-9;
+
+        if (!is_float_close(this->f_norm_eps, other.f_norm_eps, EPSILON)) return true;
+        if (!is_float_close(this->f_norm_rms_eps, other.f_norm_rms_eps, EPSILON)) return true;
+        if (!is_float_close(this->rope_freq_base_train, other.rope_freq_base_train, EPSILON)) return true;
+        if (!is_float_close(this->rope_freq_scale_train, other.rope_freq_scale_train, EPSILON)) return true;
+
+        return false;
     }
 
     uint32_t n_gqa() const {
@@ -8181,14 +8219,14 @@ void llama_print_timings(struct llama_context * ctx) {
     const llama_timings timings = llama_get_timings(ctx);
 
     LLAMA_LOG_INFO("\n");
-    LLAMA_LOG_INFO("%s:        load time = %8.2f ms\n", __func__, timings.t_load_ms);
-    LLAMA_LOG_INFO("%s:      sample time = %8.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s:        load time = %10.2f ms\n", __func__, timings.t_load_ms);
+    LLAMA_LOG_INFO("%s:      sample time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_sample_ms, timings.n_sample, timings.t_sample_ms / timings.n_sample, 1e3 / timings.t_sample_ms * timings.n_sample);
-    LLAMA_LOG_INFO("%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s: prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_p_eval_ms, timings.n_p_eval, timings.t_p_eval_ms / timings.n_p_eval, 1e3 / timings.t_p_eval_ms * timings.n_p_eval);
-    LLAMA_LOG_INFO("%s:        eval time = %8.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s:        eval time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_eval_ms, timings.n_eval, timings.t_eval_ms / timings.n_eval, 1e3 / timings.t_eval_ms * timings.n_eval);
-    LLAMA_LOG_INFO("%s:       total time = %8.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
+    LLAMA_LOG_INFO("%s:       total time = %10.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
 }
 
 void llama_reset_timings(struct llama_context * ctx) {

prompts/LLM-questions.txt

@@ -0,0 +1,49 @@
+In the context of LLMs, what is "Attention"?
+In the context of LLMs, what is a completion?
+In the context of LLMs, what is a prompt?
+In the context of LLMs, what is GELU?
+In the context of LLMs, what is RELU?
+In the context of LLMs, what is softmax?
+In the context of LLMs, what is decoding?
+In the context of LLMs, what is encoding?
+In the context of LLMs, what is tokenizing?
+In the context of LLMs, what is an embedding?
+In the context of LLMs, what is quantization?
+In the context of LLMs, what is a tensor?
+In the context of LLMs, what is a sparse tensor?
+In the context of LLMs, what is a vector?
+In the context of LLMs, how is attention implemented?
+In the context of LLMs, why is attention all you need?
+In the context of LLMs, what is "RoPe" and what is it used for?
+In the context of LLMs, what is "LoRA" and what is it used for?
+In the context of LLMs, what are weights?
+In the context of LLMs, what are biases?
+In the context of LLMs, what are checkpoints?
+In the context of LLMs, what is "perplexity"?
+In the context of LLMs, what are models?
+In the context of machine-learning, what is "catastrophic forgetting"?
+In the context of machine-learning, what is "elastic weight consolidation (EWC)"?
+In the context of neural nets, what is a hidden layer?
+In the context of neural nets, what is a convolution?
+In the context of neural nets, what is dropout?
+In the context of neural nets, what is cross-entropy?
+In the context of neural nets, what is over-fitting?
+In the context of neural nets, what is under-fitting?
+What is the difference between an interpreted computer language and a compiled computer language?
+In the context of software development, what is a debugger?
+When processing using a GPU, what is off-loading?
+When processing using a GPU, what is a batch?
+When processing using a GPU, what is a block?
+When processing using a GPU, what is the difference between a batch and a block?
+When processing using a GPU, what is a scratch tensor?
+When processing using a GPU, what is a layer?
+When processing using a GPU, what is a cache?
+When processing using a GPU, what is unified memory?
+When processing using a GPU, what is VRAM?
+When processing using a GPU, what is a kernel?
+When processing using a GPU, what is "metal"?
+In the context of LLMs, what are "Zero-Shot", "One-Shot" and "Few-Shot" learning models?
+In the context of LLMs, what is the "Transformer-model" architecture?
+In the context of LLMs, what is "Multi-Head Attention"?
+In the context of LLMs, what is "Self-Attention"?
+In the context of transformer-model architectures, how do attention mechanisms use masks?

prompts/parallel-questions.txt

@@ -0,0 +1,42 @@
+What do you know about Hobbits?
+What is quantum field theory?
+Why did the chicken cross the road?
+Who is the president of the United States?
+How do I run CMake on MacOS?
+Do you agree that C++ is a really finicky language compared with Python3?
+Is it a good idea to invest in technology?
+Do you like Wagner's Ring?
+Do you think this file input option is really neat?
+What should we all do about climate change?
+Is time-travel possible within the laws of current physics?
+Is it like anything to be a bat?
+Once the chicken has crossed the road, does it try to go back?
+Who is the greatest of all musical composers?
+What is art?
+Is there life elsewhere in the universe?
+What is intelligence?
+What is the difference between knowledge and intelligence?
+Will religion ever die?
+Do we understand ourselves?
+What is the best way to cook eggs?
+If you cannot see things, on what basis do you evaluate them?
+Explain the role of the np junction in photovoltaic cells?
+Is professional sport a good or bad influence on human behaviour?
+Is capital punishment immoral?
+Should we care about other people?
+Who are you?
+Which sense would you surrender if you could?
+Was Henry Ford a hero or a villain?
+Do we need leaders?
+What is nucleosynthesis?
+Who is the greatest scientist of all time?
+Who first observed what came to be known as the photovoltaic effect?
+What is nuclear fusion and why does it release energy?
+Can you know that you exist?
+What is an exoplanet?
+Do you like cream?
+What is the difference?
+Can I know that I exist while I'm dreaming that I'm Descartes?
+Who said "I didn't know I thought that until I heard myself saying it"?
+Does anything really matter?
+Can you explain the unreasonable effectiveness of mathematics?