diff --git a/gpt4all-backend/replit_impl.h b/gpt4all-backend/replit_impl.h deleted file mode 100644 index 97e07fa9..00000000 --- a/gpt4all-backend/replit_impl.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef REPLIT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE -#error This file is NOT meant to be included outside of replit.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define REPLIT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE -#endif -#ifndef REPLIT_H -#define REPLIT_H - -#include -#include -#include -#include "llmodel.h" - -#define GGML_QNT_VERSION_FACTOR 1000 // do not change this - -struct ReplitPrivate; -class Replit : public LLModel { -public: - Replit(); - ~Replit(); - - bool supportsEmbedding() const override { return false; } - bool supportsCompletion() const override { return true; } - bool loadModel(const std::string &modelPath) override; - bool isModelLoaded() const override; - size_t requiredMem(const std::string & modelPath) override; - size_t stateSize() const override; - size_t saveState(uint8_t *dest) const override; - size_t restoreState(const uint8_t *src) override; - void setThreadCount(int32_t n_threads) override; - int32_t threadCount() const override; - bool usingGPUDevice() override; - -private: - ReplitPrivate *d_ptr; - -protected: - std::vector tokenize(PromptContext &, const std::string&) const override; - std::string tokenToString(Token) const override; - Token sampleToken(PromptContext &ctx) const override; - bool evalTokens(PromptContext &ctx, const std::vector &tokens) const override; - int32_t contextLength() const override; - const std::vector& endTokens() const override; -}; - -#endif // REPLIT_H diff --git a/gpt4all-backend/starcoder_impl.h b/gpt4all-backend/starcoder_impl.h deleted file mode 100644 index 1a0136e7..00000000 --- a/gpt4all-backend/starcoder_impl.h +++ /dev/null @@ -1,42 +0,0 @@ -#ifndef STARCODER_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE -#error This file is NOT meant to be included outside of starcoder.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define STARCODER_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE -#endif -#ifndef STARCODER_H -#define STARCODER_H - -#include -#include -#include -#include -#include "llmodel.h" - -struct StarcoderPrivate; -class Starcoder : public LLModel { -public: - Starcoder(); - ~Starcoder(); - - bool supportsEmbedding() const override { return false; } - bool supportsCompletion() const override { return true; } - bool loadModel(const std::string &modelPath) override; - bool isModelLoaded() const override; - size_t requiredMem(const std::string &modelPath) override; - size_t stateSize() const override; - size_t saveState(uint8_t *dest) const override; - size_t restoreState(const uint8_t *src) override; - void setThreadCount(int32_t n_threads) override; - int32_t threadCount() const override; - -private: - std::unique_ptr d_ptr; - -protected: - std::vector tokenize(PromptContext &, const std::string&) const override; - Token sampleToken(PromptContext &ctx) const override; - std::string tokenToString(Token) const override; - bool evalTokens(PromptContext &ctx, const std::vector &tokens) const override; - int32_t contextLength() const override; - const std::vector& endTokens() const override; -}; - -#endif // STARCODER_H diff --git a/gpt4all-chat/CMakeLists.txt b/gpt4all-chat/CMakeLists.txt index 108dc5eb..2282c17b 100644 --- a/gpt4all-chat/CMakeLists.txt +++ b/gpt4all-chat/CMakeLists.txt @@ -189,19 +189,10 @@ install(TARGETS llamamodel-mainline-default DESTINATION lib COMPONENT ${COMPONEN if(APPLE) install(TARGETS llamamodel-mainline-metal DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) endif() -install(TARGETS falcon-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -install(TARGETS falcon-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -#install(TARGETS mpt-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -#install(TARGETS mpt-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -install(TARGETS replit-mainline-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -install(TARGETS replit-mainline-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -if(APPLE) -install(TARGETS replit-mainline-metal DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -endif() +install(TARGETS mpt-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) +install(TARGETS mpt-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) install(TARGETS bert-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) install(TARGETS bert-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -install(TARGETS starcoder-avxonly DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) -install(TARGETS starcoder-default DESTINATION lib COMPONENT ${COMPONENT_NAME_MAIN}) set(CPACK_GENERATOR "IFW") set(CPACK_VERBATIM_VARIABLES YES) diff --git a/gpt4all-chat/chatllm.cpp b/gpt4all-chat/chatllm.cpp index b17bf500..6f008062 100644 --- a/gpt4all-chat/chatllm.cpp +++ b/gpt4all-chat/chatllm.cpp @@ -11,11 +11,8 @@ #define MPT_INTERNAL_STATE_VERSION 0 #define GPTJ_INTERNAL_STATE_VERSION 0 -#define REPLIT_INTERNAL_STATE_VERSION 0 #define LLAMA_INTERNAL_STATE_VERSION 0 -#define FALCON_INTERNAL_STATE_VERSION 0 #define BERT_INTERNAL_STATE_VERSION 0 -#define STARCODER_INTERNAL_STATE_VERSION 0 class LLModelStore { public: @@ -311,10 +308,7 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo) case 'L': m_llModelType = LLModelType::LLAMA_; break; case 'G': m_llModelType = LLModelType::GPTJ_; break; case 'M': m_llModelType = LLModelType::MPT_; break; - case 'R': m_llModelType = LLModelType::REPLIT_; break; - case 'F': m_llModelType = LLModelType::FALCON_; break; case 'B': m_llModelType = LLModelType::BERT_; break; - case 'S': m_llModelType = LLModelType::STARCODER_; break; default: { delete m_llModelInfo.model; @@ -717,13 +711,10 @@ bool ChatLLM::serialize(QDataStream &stream, int version) if (version > 1) { stream << m_llModelType; switch (m_llModelType) { - case REPLIT_: stream << REPLIT_INTERNAL_STATE_VERSION; break; case MPT_: stream << MPT_INTERNAL_STATE_VERSION; break; case GPTJ_: stream << GPTJ_INTERNAL_STATE_VERSION; break; case LLAMA_: stream << LLAMA_INTERNAL_STATE_VERSION; break; - case FALCON_: stream << FALCON_INTERNAL_STATE_VERSION; break; case BERT_: stream << BERT_INTERNAL_STATE_VERSION; break; - case STARCODER_: stream << STARCODER_INTERNAL_STATE_VERSION; break; default: Q_UNREACHABLE(); } } @@ -880,4 +871,4 @@ void ChatLLM::processSystemPrompt() fflush(stdout); #endif m_processedSystemPrompt = true; -} \ No newline at end of file +} diff --git a/gpt4all-chat/chatllm.h b/gpt4all-chat/chatllm.h index 724ccefa..7e0b51eb 100644 --- a/gpt4all-chat/chatllm.h +++ b/gpt4all-chat/chatllm.h @@ -14,10 +14,7 @@ enum LLModelType { GPTJ_, LLAMA_, CHATGPT_, - REPLIT_, - FALCON_, BERT_, - STARCODER_ }; struct LLModelInfo { diff --git a/gpt4all-chat/cmake/deploy-qt-mac.cmake.in b/gpt4all-chat/cmake/deploy-qt-mac.cmake.in index 488335aa..b33494e7 100644 --- a/gpt4all-chat/cmake/deploy-qt-mac.cmake.in +++ b/gpt4all-chat/cmake/deploy-qt-mac.cmake.in @@ -5,10 +5,7 @@ execute_process(COMMAND ${MACDEPLOYQT} ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/pack file(GLOB MYGPTJLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libgptj*) file(GLOB MYMPTLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libmpt*) file(GLOB MYLLAMALIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libllama*) -file(GLOB MYREPLITLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libreplit*) -file(GLOB MYFALCONLLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libfalcon*) file(GLOB MYBERTLLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libbert*) -file(GLOB MYSTARCODERLLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libstarcoder*) file(GLOB MYLLMODELLIBS ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/lib/libllmodel.*) file(COPY ${MYGPTJLIBS} DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) @@ -16,14 +13,8 @@ file(COPY ${MYMPTLIBS} DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) file(COPY ${MYLLAMALIBS} DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) -file(COPY ${MYREPLITLIBS} - DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) -file(COPY ${MYFALCONLLIBS} - DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) file(COPY ${MYBERTLLIBS} DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) -file(COPY ${MYSTARCODERLLIBS} - DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) file(COPY ${MYLLAMALIBS} DESTINATION ${CPACK_TEMPORARY_INSTALL_DIRECTORY}/packages/${COMPONENT_NAME_MAIN}/data/bin/gpt4all.app/Contents/Frameworks) file(COPY ${MYLLMODELLIBS}