* Don't stop generating at end of context
* Use llama_kv_cache ops to shift context
* Fix and improve reverse prompt detection
* Replace prompt recalc callback with a flag to disallow context shift
* user can configure the prompt and when they appear
* also make the name generation prompt configurable
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
* prevent load progress from getting out of sync with the current chat
* fix memory leak on exit if the LLModelStore contains a model
* do not report cancellation as a failure in console/Mixpanel
* show "waiting for model" separately from "switching context" in UI
* do not show lower "reload" button on error
* skip context switch if unload is pending
* skip unnecessary calls to LLModel::saveState
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Other changes:
- Always display first start dialog if privacy options are unset (e.g. if the user closed GPT4All without selecting them)
- LocalDocs scanQueue is now always deferred
- Fix a potential crash in magic_match
- LocalDocs indexing is now started after the first start dialog is dismissed so usage stats are included
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
per model settings as well as the ability to clone a model into a "character."
This also implements system prompts as well as quite a few bugfixes for
instance this fixes chatgpt.
* porting over replit code model to gpt4all
* replaced memory with kv_self struct
* continuing debug
* welp it built but lot of sus things
* working model loading and somewhat working generate.. need to format response?
* revert back to semi working version
* finally got rid of weird formatting
* figured out problem is with python bindings - this is good to go for testing
* addressing PR feedback
* output refactor
* fixed prompt reponse collection
* cleanup
* addressing PR comments
* building replit backend with new ggmlver code
* chatllm replit and clean python files
* cleanup
* updated replit to match new llmodel api
* match llmodel api and change size_t to Token
* resolve PR comments
* replit model commit comment
