merged changes

.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

.gitignore

@@ -10,6 +10,7 @@
 *.gcno
 *.gcda
 *.dot
+*.metallib
 .DS_Store
 .build/
 .cache/

Package.swift

@@ -10,15 +10,18 @@ let platforms: [SupportedPlatform]? = [
     .tvOS(.v14)
 ]
 let exclude: [String] = []
-let additionalSources: [String] = ["ggml-metal.m", "ggml-metal.metal"]
+let resources: [Resource] = [
+    .process("ggml-metal.metal")
+]
+let additionalSources: [String] = ["ggml-metal.m"]
 let additionalSettings: [CSetting] = [
     .unsafeFlags(["-fno-objc-arc"]),
-    .define("GGML_SWIFT"),
     .define("GGML_USE_METAL")
 ]
 #else
 let platforms: [SupportedPlatform]? = nil
 let exclude: [String] = ["ggml-metal.metal"]
+let resources: [Resource] = []
 let additionalSources: [String] = []
 let additionalSettings: [CSetting] = []
 #endif
@@ -40,6 +43,7 @@ let package = Package(
                 "ggml-alloc.c",
                 "k_quants.c",
             ] + additionalSources,
+            resources: resources,
             publicHeadersPath: "spm-headers",
             cSettings: [
                 .unsafeFlags(["-Wno-shorten-64-to-32"]),

README.md

@@ -95,6 +95,7 @@ as the main playground for developing new features for the [ggml](https://github
 - [X] [Aquila-7B](https://huggingface.co/BAAI/Aquila-7B) / [AquilaChat-7B](https://huggingface.co/BAAI/AquilaChat-7B)
 - [X] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187)
 - [X] [Mistral AI v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+- [X] [Refact](https://huggingface.co/smallcloudai/Refact-1_6B-fim)
 
 **Bindings:**
 
@@ -377,7 +378,7 @@ Building the program with BLAS support may lead to some performance improvements
 
 - #### cuBLAS
 
-  This provides BLAS acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).
+  This provides BLAS acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager (e.g. `apt install nvidia-cuda-toolkit`) or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).
   - Using `make`:
     ```bash
     make LLAMA_CUBLAS=1
@@ -613,6 +614,18 @@ For more information, see [https://huggingface.co/docs/transformers/perplexity](
 The perplexity measurements in table above are done against the `wikitext2` test dataset (https://paperswithcode.com/dataset/wikitext-2), with context length of 512.
 The time per token is measured on a MacBook M1 Pro 32GB RAM using 4 and 8 threads.
 
+#### How to run
+
+1. Download/extract: https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip?ref=salesforce-research
+2. Run `./perplexity -m models/7B/ggml-model-q4_0.gguf -f wiki.test.raw`
+3. Output:
+```
+perplexity : calculating perplexity over 655 chunks
+24.43 seconds per pass - ETA 4.45 hours
+[1]4.5970,[2]5.1807,[3]6.0382,...
+```
+And after 4.45 hours, you will have the final perplexity.
+
 ### Interactive mode
 
 If you want a more ChatGPT-like experience, you can run in interactive mode by passing `-i` as a parameter.
@@ -775,18 +788,6 @@ If your issue is with model generation quality, then please at least scan the fo
     - [Aligning language models to follow instructions](https://openai.com/research/instruction-following)
     - [Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
 
-#### How to run
-
-1. Download/extract: https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip?ref=salesforce-research
-2. Run `./perplexity -m models/7B/ggml-model-q4_0.gguf -f wiki.test.raw`
-3. Output:
-```
-perplexity : calculating perplexity over 655 chunks
-24.43 seconds per pass - ETA 4.45 hours
-[1]4.5970,[2]5.1807,[3]6.0382,...
-```
-And after 4.45 hours, you will have the final perplexity.
-
 ### Android
 
 #### Building the Project using Android NDK

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();
@@ -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-persimmon-to-gguf.py

@@ -0,0 +1,130 @@
+import torch
+import os
+from pprint import pprint
+import sys
+import argparse
+from pathlib import Path
+from sentencepiece import SentencePieceProcessor
+if 'NO_LOCAL_GGUF' not in os.environ:
+    sys.path.insert(1, str(Path(__file__).parent / 'gguf-py' / 'gguf'))
+import gguf
+
+def _flatten_dict(dct, tensors, prefix=None):
+    assert isinstance(dct, dict)
+    for key in dct.keys():
+        new_prefix = prefix + '.' + key if prefix is not None else key
+        if isinstance(dct[key], torch.Tensor):
+            tensors[new_prefix] = dct[key]
+        elif isinstance(dct[key], dict):
+            _flatten_dict(dct[key], tensors, new_prefix)
+        else:
+            raise ValueError(type(dct[key]))
+    return None
+
+def _get_sentencepiece_tokenizer_info(dir_model: Path):
+    tokenizer_path = dir_model / 'adept_vocab.model'
+    print('gguf: getting sentencepiece tokenizer from', tokenizer_path)
+    tokenizer = SentencePieceProcessor(str(tokenizer_path))
+    print('gguf: adding tokens')
+    tokens: list[bytes] = []
+    scores: list[float] = []
+    toktypes: list[int] = []
+
+    for i in range(tokenizer.vocab_size()):
+        text: bytes
+        score: float
+
+        piece = tokenizer.id_to_piece(i)
+        text = piece.encode("utf-8")
+        score = tokenizer.get_score(i)
+
+        toktype = 1
+        if tokenizer.is_unknown(i):
+            toktype = 2
+        if tokenizer.is_control(i):
+            toktype = 3
+        if tokenizer.is_unused(i):
+            toktype = 5
+        if tokenizer.is_byte(i):
+            toktype = 6
+
+        tokens.append(text)
+        scores.append(score)
+        toktypes.append(toktype)
+        pass
+    return tokens, scores, toktypes
+
+def main():
+    parser = argparse.ArgumentParser(description="Convert a Persimmon model from Adept (e.g. Persimmon 8b chat) to a GGML compatible file")
+    parser.add_argument("--outfile",             type=Path, help="path to write to; default: based on input")
+    parser.add_argument("--ckpt-path",           type=Path, help="path to persimmon checkpoint .pt file")
+    parser.add_argument("--model-dir",           type=Path, help="directory containing model e.g. 8b_chat_model_release")
+    parser.add_argument("--adept-inference-dir", type=str, help="path to adept-inference code directory")
+    args = parser.parse_args()
+    sys.path.append(str(args.adept_inference_dir))
+    persimmon_model = torch.load(args.ckpt_path)
+    hparams = persimmon_model['args']
+    pprint(hparams)
+    tensors = {}
+    _flatten_dict(persimmon_model['model'], tensors, None)
+
+    arch = gguf.MODEL_ARCH.PERSIMMON
+    gguf_writer = gguf.GGUFWriter(args.outfile, gguf.MODEL_ARCH_NAMES[arch])
+
+    block_count = hparams.num_layers
+    head_count = hparams.num_attention_heads
+    head_count_kv = head_count
+    ctx_length = hparams.seq_length
+    hidden_size = hparams.hidden_size
+
+    gguf_writer.add_name('persimmon-8b-chat')
+    gguf_writer.add_context_length(ctx_length)
+    gguf_writer.add_embedding_length(hidden_size)
+    gguf_writer.add_block_count(block_count)
+    gguf_writer.add_feed_forward_length(hparams.ffn_hidden_size)
+    gguf_writer.add_rope_dimension_count(hidden_size // head_count)
+    gguf_writer.add_head_count(head_count)
+    gguf_writer.add_head_count_kv(head_count_kv)
+    gguf_writer.add_rope_freq_base(hparams.rotary_emb_base)
+    gguf_writer.add_layer_norm_eps(hparams.layernorm_epsilon)
+
+    tokens, scores, toktypes = _get_sentencepiece_tokenizer_info(args.model_dir)
+    gguf_writer.add_tokenizer_model('llama')
+    gguf_writer.add_token_list(tokens)
+    gguf_writer.add_token_scores(scores)
+    gguf_writer.add_token_types(toktypes)
+    gguf_writer.add_bos_token_id(71013)
+    gguf_writer.add_eos_token_id(71013)
+
+    tensor_map = gguf.get_tensor_name_map(arch, block_count)
+    print(tensor_map)
+    for name in tensors.keys():
+        data = tensors[name]
+        if name.endswith(".self_attention.rotary_emb.inv_freq"):
+            continue
+        old_dtype = data.dtype
+        # TODO: FP16 conversion produces garbage outputs. (Q8_0 does not, so..?)
+        data = data.to(torch.float32).squeeze().numpy()
+        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)
+        print(new_name + ", n_dims = " + str(n_dims) + ", " + str(old_dtype) + " --> " + str(data.dtype))
+        gguf_writer.add_tensor(new_name, data)
+    print("gguf: write header")
+    gguf_writer.write_header_to_file()
+    print("gguf: write metadata")
+    gguf_writer.write_kv_data_to_file()
+    print("gguf: write tensors")
+    gguf_writer.write_tensors_to_file()
+
+    gguf_writer.close()
+
+    print(f"gguf: model successfully exported to '{args.outfile}'")
+    print("")
+
+
+
+if __name__ == '__main__':
+    main()

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);