.dockerignore
.gitignore
.gitmodules
.readthedocs.yaml
CHANGELOG.md
CMakeLists.txt
LICENSE.md
Makefile
README.md
mkdocs.yml
poetry.lock
poetry.toml
pyproject.toml
setup.py
.github/dependabot.yml
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/workflows/build-and-release.yaml
.github/workflows/build-docker.yaml
.github/workflows/publish-to-test.yaml
.github/workflows/publish.yaml
.github/workflows/test-pypi.yaml
.github/workflows/test.yaml
docker/README.md
docker/cuda_simple/Dockerfile
docker/open_llama/Dockerfile
docker/open_llama/build.sh
docker/open_llama/hug_model.py
docker/open_llama/start.sh
docker/open_llama/start_server.sh
docker/openblas_simple/Dockerfile
docker/simple/Dockerfile
docker/simple/run.sh
docs/api-reference.md
docs/index.md
docs/requirements.txt
docs/install/macos.md
examples/high_level_api/fastapi_server.py
examples/high_level_api/high_level_api_embedding.py
examples/high_level_api/high_level_api_inference.py
examples/high_level_api/high_level_api_streaming.py
examples/high_level_api/langchain_custom_llm.py
examples/low_level_api/Chat.py
examples/low_level_api/Miku.py
examples/low_level_api/ReasonAct.py
examples/low_level_api/common.py
examples/low_level_api/low_level_api_chat_cpp.py
examples/low_level_api/low_level_api_llama_cpp.py
examples/low_level_api/quantize.py
examples/low_level_api/util.py
examples/notebooks/Clients.ipynb
examples/notebooks/Guidance.ipynb
examples/notebooks/PerformanceTuning.ipynb
llama_cpp/__init__.py
llama_cpp/llama.py
llama_cpp/llama_cpp.py
llama_cpp/llama_grammar.py
llama_cpp/llama_types.py
llama_cpp/py.typed
llama_cpp/utils.py
llama_cpp/version.py
llama_cpp/server/__init__.py
llama_cpp/server/__main__.py
llama_cpp/server/app.py
llama_cpp_python.egg-info/PKG-INFO
llama_cpp_python.egg-info/SOURCES.txt
llama_cpp_python.egg-info/dependency_links.txt
llama_cpp_python.egg-info/requires.txt
llama_cpp_python.egg-info/top_level.txt
tests/test_llama.py
vendor/llama.cpp/.clang-tidy
vendor/llama.cpp/.dockerignore
vendor/llama.cpp/.ecrc
vendor/llama.cpp/.editorconfig
vendor/llama.cpp/.flake8
vendor/llama.cpp/.gitignore
vendor/llama.cpp/.pre-commit-config.yaml
vendor/llama.cpp/CMakeLists.txt
vendor/llama.cpp/LICENSE
vendor/llama.cpp/Makefile
vendor/llama.cpp/Package.swift
vendor/llama.cpp/README.md
vendor/llama.cpp/SHA256SUMS
vendor/llama.cpp/build.zig
vendor/llama.cpp/codecov.yml
vendor/llama.cpp/convert-falcon-hf-to-gguf.py
vendor/llama.cpp/convert-gptneox-hf-to-gguf.py
vendor/llama.cpp/convert-llama-ggml-to-gguf.py
vendor/llama.cpp/convert-lora-to-ggml.py
vendor/llama.cpp/convert.py
vendor/llama.cpp/flake.lock
vendor/llama.cpp/flake.nix
vendor/llama.cpp/ggml-alloc.c
vendor/llama.cpp/ggml-alloc.h
vendor/llama.cpp/ggml-cuda.cu
vendor/llama.cpp/ggml-cuda.h
vendor/llama.cpp/ggml-metal.h
vendor/llama.cpp/ggml-metal.m
vendor/llama.cpp/ggml-metal.metal
vendor/llama.cpp/ggml-mpi.c
vendor/llama.cpp/ggml-mpi.h
vendor/llama.cpp/ggml-opencl.cpp
vendor/llama.cpp/ggml-opencl.h
vendor/llama.cpp/ggml.c
vendor/llama.cpp/ggml.h
vendor/llama.cpp/k_quants.c
vendor/llama.cpp/k_quants.h
vendor/llama.cpp/llama.cpp
vendor/llama.cpp/llama.h
vendor/llama.cpp/mypy.ini
vendor/llama.cpp/requirements.txt
vendor/llama.cpp/run_with_preset.py
vendor/llama.cpp/.devops/full-cuda.Dockerfile
vendor/llama.cpp/.devops/full-rocm.Dockerfile
vendor/llama.cpp/.devops/full.Dockerfile
vendor/llama.cpp/.devops/llama-cpp-clblast.srpm.spec
vendor/llama.cpp/.devops/llama-cpp-cublas.srpm.spec
vendor/llama.cpp/.devops/llama-cpp.srpm.spec
vendor/llama.cpp/.devops/main-cuda.Dockerfile
vendor/llama.cpp/.devops/main-rocm.Dockerfile
vendor/llama.cpp/.devops/main.Dockerfile
vendor/llama.cpp/.devops/tools.sh
vendor/llama.cpp/.github/ISSUE_TEMPLATE/custom.md
vendor/llama.cpp/.github/workflows/build.yml
vendor/llama.cpp/.github/workflows/code-coverage.yml
vendor/llama.cpp/.github/workflows/docker.yml
vendor/llama.cpp/.github/workflows/editorconfig.yml
vendor/llama.cpp/.github/workflows/gguf-publish.yml
vendor/llama.cpp/.github/workflows/tidy-post.yml
vendor/llama.cpp/.github/workflows/tidy-review.yml
vendor/llama.cpp/ci/README.md
vendor/llama.cpp/ci/run.sh
vendor/llama.cpp/common/CMakeLists.txt
vendor/llama.cpp/common/common.cpp
vendor/llama.cpp/common/common.h
vendor/llama.cpp/common/console.cpp
vendor/llama.cpp/common/console.h
vendor/llama.cpp/common/grammar-parser.cpp
vendor/llama.cpp/common/grammar-parser.h
vendor/llama.cpp/common/log.h
vendor/llama.cpp/docs/BLIS.md
vendor/llama.cpp/docs/token_generation_performance_tips.md
vendor/llama.cpp/examples/CMakeLists.txt
vendor/llama.cpp/examples/Miku.sh
vendor/llama.cpp/examples/alpaca.sh
vendor/llama.cpp/examples/chat-13B.bat
vendor/llama.cpp/examples/chat-13B.sh
vendor/llama.cpp/examples/chat-persistent.sh
vendor/llama.cpp/examples/chat-vicuna.sh
vendor/llama.cpp/examples/chat.sh
vendor/llama.cpp/examples/gpt4all.sh
vendor/llama.cpp/examples/json-schema-to-grammar.py
vendor/llama.cpp/examples/llama.vim
vendor/llama.cpp/examples/llama2-13b.sh
vendor/llama.cpp/examples/llama2.sh
vendor/llama.cpp/examples/llm.vim
vendor/llama.cpp/examples/make-ggml.py
vendor/llama.cpp/examples/reason-act.sh
vendor/llama.cpp/examples/server-llama2-13B.sh
vendor/llama.cpp/examples/baby-llama/CMakeLists.txt
vendor/llama.cpp/examples/baby-llama/baby-llama.cpp
vendor/llama.cpp/examples/beam-search/CMakeLists.txt
vendor/llama.cpp/examples/beam-search/beam-search.cpp
vendor/llama.cpp/examples/benchmark/CMakeLists.txt
vendor/llama.cpp/examples/benchmark/benchmark-matmult.cpp
vendor/llama.cpp/examples/convert-llama2c-to-ggml/CMakeLists.txt
vendor/llama.cpp/examples/convert-llama2c-to-ggml/README.md
vendor/llama.cpp/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
vendor/llama.cpp/examples/embd-input/.gitignore
vendor/llama.cpp/examples/embd-input/CMakeLists.txt
vendor/llama.cpp/examples/embd-input/README.md
vendor/llama.cpp/examples/embd-input/embd-input-lib.cpp
vendor/llama.cpp/examples/embd-input/embd-input-test.cpp
vendor/llama.cpp/examples/embd-input/embd-input.h
vendor/llama.cpp/examples/embd-input/embd_input.py
vendor/llama.cpp/examples/embd-input/llava.py
vendor/llama.cpp/examples/embd-input/minigpt4.py
vendor/llama.cpp/examples/embd-input/panda_gpt.py
vendor/llama.cpp/examples/embedding/CMakeLists.txt
vendor/llama.cpp/examples/embedding/README.md
vendor/llama.cpp/examples/embedding/embedding.cpp
vendor/llama.cpp/examples/gguf/CMakeLists.txt
vendor/llama.cpp/examples/gguf/gguf.cpp
vendor/llama.cpp/examples/gptneox-wip/cmpnct_gpt2bpe.hpp
vendor/llama.cpp/examples/gptneox-wip/falcon-main.cpp
vendor/llama.cpp/examples/gptneox-wip/gptneox-main.cpp
vendor/llama.cpp/examples/jeopardy/README.md
vendor/llama.cpp/examples/jeopardy/graph.py
vendor/llama.cpp/examples/jeopardy/jeopardy.sh
vendor/llama.cpp/examples/jeopardy/qasheet.csv
vendor/llama.cpp/examples/jeopardy/questions.txt
vendor/llama.cpp/examples/llama-bench/CMakeLists.txt
vendor/llama.cpp/examples/llama-bench/llama-bench.cpp
vendor/llama.cpp/examples/main/CMakeLists.txt
vendor/llama.cpp/examples/main/README.md
vendor/llama.cpp/examples/main/main.cpp
vendor/llama.cpp/examples/metal/CMakeLists.txt
vendor/llama.cpp/examples/metal/metal.cpp
vendor/llama.cpp/examples/perplexity/CMakeLists.txt
vendor/llama.cpp/examples/perplexity/README.md
vendor/llama.cpp/examples/perplexity/perplexity.cpp
vendor/llama.cpp/examples/quantize/CMakeLists.txt
vendor/llama.cpp/examples/quantize/README.md
vendor/llama.cpp/examples/quantize/quantize.cpp
vendor/llama.cpp/examples/quantize-stats/CMakeLists.txt
vendor/llama.cpp/examples/quantize-stats/quantize-stats.cpp
vendor/llama.cpp/examples/save-load-state/CMakeLists.txt
vendor/llama.cpp/examples/save-load-state/save-load-state.cpp
vendor/llama.cpp/examples/server/CMakeLists.txt
vendor/llama.cpp/examples/server/README.md
vendor/llama.cpp/examples/server/api_like_OAI.py
vendor/llama.cpp/examples/server/chat-llama2.sh
vendor/llama.cpp/examples/server/chat.mjs
vendor/llama.cpp/examples/server/chat.sh
vendor/llama.cpp/examples/server/completion.js.hpp
vendor/llama.cpp/examples/server/deps.sh
vendor/llama.cpp/examples/server/httplib.h
vendor/llama.cpp/examples/server/index.html.hpp
vendor/llama.cpp/examples/server/index.js.hpp
vendor/llama.cpp/examples/server/json-schema-to-grammar.mjs.hpp
vendor/llama.cpp/examples/server/json.hpp
vendor/llama.cpp/examples/server/server.cpp
vendor/llama.cpp/examples/server/public/completion.js
vendor/llama.cpp/examples/server/public/index.html
vendor/llama.cpp/examples/server/public/index.js
vendor/llama.cpp/examples/server/public/json-schema-to-grammar.mjs
vendor/llama.cpp/examples/simple/CMakeLists.txt
vendor/llama.cpp/examples/simple/simple.cpp
vendor/llama.cpp/examples/speculative/CMakeLists.txt
vendor/llama.cpp/examples/speculative/speculative.cpp
vendor/llama.cpp/examples/train-text-from-scratch/CMakeLists.txt
vendor/llama.cpp/examples/train-text-from-scratch/README.md
vendor/llama.cpp/examples/train-text-from-scratch/convert-train-checkpoint-to-gguf.py
vendor/llama.cpp/examples/train-text-from-scratch/train-text-from-scratch.cpp
vendor/llama.cpp/gguf-py/LICENSE
vendor/llama.cpp/gguf-py/README.md
vendor/llama.cpp/gguf-py/pyproject.toml
vendor/llama.cpp/gguf-py/gguf/__init__.py
vendor/llama.cpp/gguf-py/gguf/gguf.py
vendor/llama.cpp/gguf-py/gguf/py.typed
vendor/llama.cpp/gguf-py/tests/test_gguf.py
vendor/llama.cpp/grammars/README.md
vendor/llama.cpp/grammars/arithmetic.gbnf
vendor/llama.cpp/grammars/c.gbnf
vendor/llama.cpp/grammars/chess.gbnf
vendor/llama.cpp/grammars/japanese.gbnf
vendor/llama.cpp/grammars/json.gbnf
vendor/llama.cpp/grammars/json_arr.gbnf
vendor/llama.cpp/grammars/list.gbnf
vendor/llama.cpp/media/llama-leader.jpeg
vendor/llama.cpp/media/llama0-banner.png
vendor/llama.cpp/media/llama0-logo.png
vendor/llama.cpp/media/llama1-banner.png
vendor/llama.cpp/media/llama1-logo.png
vendor/llama.cpp/models/.editorconfig
vendor/llama.cpp/models/ggml-vocab-llama.gguf
vendor/llama.cpp/pocs/CMakeLists.txt
vendor/llama.cpp/pocs/vdot/CMakeLists.txt
vendor/llama.cpp/pocs/vdot/q8dot.cpp
vendor/llama.cpp/pocs/vdot/vdot.cpp
vendor/llama.cpp/prompts/alpaca.txt
vendor/llama.cpp/prompts/chat-with-bob.txt
vendor/llama.cpp/prompts/chat-with-vicuna-v0.txt
vendor/llama.cpp/prompts/chat-with-vicuna-v1.txt
vendor/llama.cpp/prompts/chat.txt
vendor/llama.cpp/prompts/dan-modified.txt
vendor/llama.cpp/prompts/dan.txt
vendor/llama.cpp/prompts/reason-act.txt
vendor/llama.cpp/scripts/build-info.cmake
vendor/llama.cpp/scripts/build-info.h.in
vendor/llama.cpp/scripts/build-info.sh
vendor/llama.cpp/scripts/convert-gg.sh
vendor/llama.cpp/scripts/get-wikitext-2.sh
vendor/llama.cpp/scripts/qnt-all.sh
vendor/llama.cpp/scripts/run-all-perf.sh
vendor/llama.cpp/scripts/run-all-ppl.sh
vendor/llama.cpp/scripts/sync-ggml.sh
vendor/llama.cpp/scripts/verify-checksum-models.py
vendor/llama.cpp/spm-headers/ggml.h
vendor/llama.cpp/spm-headers/llama.h
vendor/llama.cpp/tests/CMakeLists.txt
vendor/llama.cpp/tests/test-c.c
vendor/llama.cpp/tests/test-double-float.cpp
vendor/llama.cpp/tests/test-grad0.cpp
vendor/llama.cpp/tests/test-grammar-parser.cpp
vendor/llama.cpp/tests/test-llama-grammar.cpp
vendor/llama.cpp/tests/test-opt.cpp
vendor/llama.cpp/tests/test-quantize-fns.cpp
vendor/llama.cpp/tests/test-quantize-perf.cpp
vendor/llama.cpp/tests/test-sampling.cpp
vendor/llama.cpp/tests/test-tokenizer-0-falcon.cpp
vendor/llama.cpp/tests/test-tokenizer-0-falcon.py
vendor/llama.cpp/tests/test-tokenizer-0-llama.cpp
vendor/llama.cpp/tests/test-tokenizer-0-llama.py
vendor/llama.cpp/tests/test-tokenizer-1.cpp