github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-08 20:09:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Embed4All: optionally count tokens, misc fixes (#2145)

Browse Source 
Key changes:
* python: optionally return token count in Embed4All.embed
* python and docs: models2.json -> models3.json
* Embed4All: require explicit prefix for unknown models
* llamamodel: fix shouldAddBOS for Bert and Nomic Bert

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-03-20 11:24:02 -04:00
committed by GitHub
parent 271e6a529c
commit 0455b80b7f
11 changed files with 105 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gpt4all-backend/llamamodel_impl.h
View File

@@ -39,10 +39,10 @@ public:
size_t embeddingSize() const override;
// user-specified prefix
void embed(const std::vector<std::string> &texts, float *embeddings, std::optional<std::string> prefix,
int dimensionality = -1, bool doMean = true, bool atlas = false) override;
int dimensionality = -1, size_t *tokenCount = nullptr, bool doMean = true, bool atlas = false) override;
// automatic prefix
void embed(const std::vector<std::string> &texts, float *embeddings, bool isRetrieval, int dimensionality = -1,
bool doMean = true, bool atlas = false) override;
size_t *tokenCount = nullptr, bool doMean = true, bool atlas = false) override;
private:
std::unique_ptr<LLamaPrivate> d_ptr;
@@ -61,7 +61,7 @@ protected:
int32_t layerCount(std::string const &modelPath) const override;
void embedInternal(const std::vector<std::string> &texts, float *embeddings, std::string prefix, int dimensionality,
bool doMean, bool atlas, const EmbModelSpec *spec);
size_t *tokenCount, bool doMean, bool atlas, const EmbModelSpec *spec);
};
#endif // LLAMAMODEL_H