github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-05 18:40:50 +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

6
gpt4all-backend/llmodel_c.h
View File

@@ -163,16 +163,20 @@ uint64_t llmodel_restore_state_data(llmodel_model model, const uint8_t *src);
* Generate a response using the model.
* @param model A pointer to the llmodel_model instance.
* @param prompt A string representing the input prompt.
* @param prompt_template A string representing the input prompt template.
* @param prompt_callback A callback function for handling the processing of prompt.
* @param response_callback A callback function for handling the generated response.
* @param recalculate_callback A callback function for handling recalculation requests.
* @param special True if special tokens in the prompt should be processed, false otherwise.
* @param ctx A pointer to the llmodel_prompt_context structure.
*/
void llmodel_prompt(llmodel_model model, const char *prompt,
const char *prompt_template,
llmodel_prompt_callback prompt_callback,
llmodel_response_callback response_callback,
llmodel_recalculate_callback recalculate_callback,
llmodel_prompt_context *ctx);
llmodel_prompt_context *ctx,
bool special);
/**
* Generate an embedding using the model.