github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-06 11:00:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix chat-style prompt templates (#1970)

Browse Source 
Also use a new version of Mistral OpenOrca.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-02-21 15:45:32 -05:00
committed by GitHub
parent b8f5c74f40
commit 4fc4d94be4
22 changed files with 429 additions and 307 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gpt4all-backend/llamamodel_impl.h
View File

@@ -19,6 +19,7 @@ public:
bool supportsEmbedding() const override { return false; }
bool supportsCompletion() const override { return true; }
bool loadModel(const std::string &modelPath, int n_ctx, int ngl) override;
bool isModelBlacklisted(const std::string &modelPath) override;
bool isModelLoaded() const override;
size_t requiredMem(const std::string &modelPath, int n_ctx, int ngl) override;
size_t stateSize() const override;
@@ -27,7 +28,7 @@ public:
void setThreadCount(int32_t n_threads) override;
int32_t threadCount() const override;
std::vector<GPUDevice> availableGPUDevices(size_t memoryRequired) const override;
bool initializeGPUDevice(size_t memoryRequired, const std::string& name) const override;
bool initializeGPUDevice(size_t memoryRequired, const std::string &name) const override;
bool initializeGPUDevice(int device, std::string *unavail_reason) const override;
bool hasGPUDevice() override;
bool usingGPUDevice() override;
@@ -36,12 +37,13 @@ private:
std::unique_ptr<LLamaPrivate> d_ptr;
protected:
std::vector<Token> 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<int32_t> &tokens) const override;
std::vector<Token> tokenize(PromptContext &ctx, const std::string &str, bool special) const override;
std::string tokenToString(Token id) const override;
Token sampleToken(PromptContext &ctx) const override;
bool evalTokens(PromptContext &ctx, const std::vector<int32_t> &tokens) const override;
int32_t contextLength() const override;
const std::vector<Token>& endTokens() const override;
const std::vector<Token> &endTokens() const override;
bool shouldAddBOS() const override;
int32_t maxContextLength(std::string const &modelPath) const override;
int32_t layerCount(std::string const &modelPath) const override;