Skip to content

Commit

Permalink
try pipoint older llama.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
@mudler
mudler committed Oct 7, 2023
1 parent 425d18a commit 51059b7
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama.cpp
Submodule llama.cpp updated 84 files
+0 −3 .dockerignore
+40 −63 .github/workflows/build.yml
+1 −7 .gitignore
+43 −64 CMakeLists.txt
+25 −73 Makefile
+3 −10 Package.swift
+16 −21 README.md
+0 −2 common/CMakeLists.txt
+52 −123 common/common.cpp
+4 −16 common/common.h
+37 −37 common/log.h
+0 −1,496 common/train.cpp
+0 −230 common/train.h
+2 −8 convert-baichuan-hf-to-gguf.py
+105 −74 convert-falcon-hf-to-gguf.py
+51 −12 convert-gptneox-hf-to-gguf.py
+0 −130 convert-persimmon-to-gguf.py
+0 −318 convert-refact-hf-to-gguf.py
+54 −8 convert-starcoder-hf-to-gguf.py
+22 −7 convert.py
+0 −2 examples/CMakeLists.txt
+141 −48 examples/baby-llama/baby-llama.cpp
+15 −24 examples/batched/batched.cpp
+2 −2 examples/beam-search/beam-search.cpp
+4 −4 examples/chat-persistent.sh
+7 −6 examples/embd-input/embd-input-lib.cpp
+1 −1 examples/embd-input/embd-input-test.cpp
+10 −11 examples/embedding/embedding.cpp
+0 −5 examples/export-lora/CMakeLists.txt
+0 −26 examples/export-lora/README.md
+0 −474 examples/export-lora/export-lora.cpp
+0 −5 examples/finetune/CMakeLists.txt
+0 −90 examples/finetune/README.md
+0 −489 examples/finetune/convert-finetune-checkpoint-to-gguf.py
+0 −1,940 examples/finetune/finetune.cpp
+0 −8 examples/infill/CMakeLists.txt
+0 −41 examples/infill/README.md
+0 −769 examples/infill/infill.cpp
+1 −1 examples/jeopardy/README.md
+50 −111 examples/llama-bench/llama-bench.cpp
+0 −10 examples/main-cmake-pkg/CMakeLists.txt
+2 −2 examples/main/README.md
+26 −29 examples/main/main.cpp
+9 −55 examples/parallel/parallel.cpp
+35 −38 examples/perplexity/perplexity.cpp
+8 −9 examples/quantize-stats/quantize-stats.cpp
+0 −1 examples/quantize/quantize.cpp
+16 −10 examples/save-load-state/save-load-state.cpp
+4 −16 examples/server/README.md
+113 −251 examples/server/server.cpp
+7 −17 examples/simple/simple.cpp
+11 −11 examples/speculative/speculative.cpp
+3 −8 examples/train-text-from-scratch/README.md
+5 −9 examples/train-text-from-scratch/convert-train-checkpoint-to-gguf.py
+1,498 −527 examples/train-text-from-scratch/train-text-from-scratch.cpp
+1 −1 flake.nix
+2 −8 ggml-alloc.c
+0 −1 ggml-alloc.h
+82 −136 ggml-cuda.cu
+45 −86 ggml-metal.m
+2 −72 ggml-metal.metal
+53 −119 ggml-opencl.cpp
+1,223 −2,356 ggml.c
+26 −86 ggml.h
+149 −293 gguf-py/gguf/gguf.py
+1 −1 gguf-py/pyproject.toml
+2 −744 k_quants.c
+529 −1,685 llama.cpp
+51 −62 llama.h
+ − models/ggml-vocab-aquila.gguf
+ − models/ggml-vocab-falcon.gguf
+4 −4 pocs/vdot/q8dot.cpp
+0 −49 prompts/LLM-questions.txt
+0 −43 prompts/parallel-questions.txt
+0 −2 scripts/LlamaConfig.cmake.in
+5 −4 tests/CMakeLists.txt
+69 −122 tests/test-grad0.cpp
+31 −2 tests/test-opt.cpp
+15 −14 tests/test-quantize-perf.cpp
+6 −15 tests/test-tokenizer-0-falcon.cpp
+5 −7 tests/test-tokenizer-0-llama.cpp
+0 −113 tests/test-tokenizer-1-bpe.cpp
+32 −11 tests/test-tokenizer-1-llama.cpp
+0 −462 unicode.h

0 comments on commit 51059b7

Please sign in to comment.