Commit Graph

23 Commits

Author SHA1 Message Date
Ettore Di Giacinto
3c3050f68e
feat(backends): Drop bert.cpp ()
* feat(backends): Drop bert.cpp

use llama.cpp 3.2 as a drop-in replacement for bert.cpp

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(tests): make test more robust

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-11-27 16:34:28 +01:00
Ettore Di Giacinto
48d0aa2f6d
models(gallery): add new models to the gallery ()
* models: add reranker and parler-tts-mini

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: chatml im_end should not have a newline

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* models(noromaid): add

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* models(llama3): add 70b, add dolphin2.9

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* models(llama3): add unholy-8b

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* models(llama3): add therapyllama3, aura

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-25 01:28:02 +02:00
Ettore Di Giacinto
b2772509b4
models(llama3): add llama3 to embedded models ()
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-19 18:23:44 +02:00
Ettore Di Giacinto
f36d86ba6d
fix(hermes-2-pro-mistral): correct dashes in template to suppress newlines ()
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-07 18:23:47 +02:00
Ettore Di Giacinto
84e0dc3246
fix(hermes-2-pro-mistral): correct stopwords ()
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-02 15:38:00 +02:00
Ettore Di Giacinto
ebb1fcedea
fix(hermes-2-pro-mistral): add stopword for toolcall ()
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-04-01 11:48:35 +02:00
Ettore Di Giacinto
3c778b538a
Update phi-2-orange.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-03-31 13:06:41 +02:00
Ettore Di Giacinto
35290e146b
fix(grammar): respect JSONmode and grammar from user input ()
* fix(grammar): Fix JSON mode and custom grammar

* tests(aio): add jsonmode test

* tests(aio): add functioncall test

* fix(aio): use hermes-2-pro-mistral as llm for CPU profile

* add phi-2-orange
2024-03-31 13:04:09 +02:00
Ettore Di Giacinto
957f428fd5
fix(tools): correctly render tools response in templates ()
* fix(tools): allow to correctly display both Functions and Tools

* models(hermes-2-pro): correctly display function results
2024-03-30 19:02:07 +01:00
Ettore Di Giacinto
3bec467a91
feat(models): add phi-2-chat, llava-1.6, bakllava, cerbero () 2024-03-22 21:12:48 +01:00
Ettore Di Giacinto
e533dcf506
feat(functions/aio): all-in-one images, function template enhancements ()
* feat(startup): allow to specify models from local files

* feat(aio): add Dockerfile, make targets, aio profiles

* feat(template): add Function and LastMessage

* add hermes2-pro-mistral

* update hermes2 definition

* feat(template): add sprig

* feat(template): expose FunctionCall

* feat(aio): switch llm for text
2024-03-21 01:12:20 +01:00
Ettore Di Giacinto
bc8f648a91
fix(doc/examples): set defaults to mirostat ()
The default sampler on some models don't return enough candidates which
leads to a false sense of randomness. Tracing back the code it looks
that with the temperature sampler there might not be enough
candidates to pick from, and since the seed and "randomness" take effect
while picking a good candidate this yields to the same results over and
over.

Fixes https://github.com/mudler/LocalAI/issues/1723 by updating the
examples and documentation to use mirostat instead.
2024-03-11 19:49:03 +01:00
Ettore Di Giacinto
feba38be36 examples(mistral-openorca): add stopword
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-22 00:15:08 +01:00
Richard Palethorpe
e46db63e06
feat(mamba): Add bagel-dpo-2.8b ()
Adds the Mamba-slimpj model fine-tuned with bagel.
https://huggingface.co/jondurbin/bagel-dpo-2.8b-v0.2

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2024-02-02 18:17:44 +01:00
Ettore Di Giacinto
555bc02665
Update codellama-7b.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-01-30 11:36:20 +01:00
Ettore Di Giacinto
072f71dfb7
Update codellama-7b.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-01-26 18:35:33 +01:00
Ettore Di Giacinto
670cee8274
Update transformers-tinyllama.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-01-26 18:29:38 +01:00
Ettore Di Giacinto
cb7512734d
transformers: correctly load automodels ()
* backends(transformers): use AutoModel with LLM types

* examples: animagine-xl

* Add codellama examples
2024-01-26 00:13:21 +01:00
Ettore Di Giacinto
5e335eaead
feat(transformers): support also text generation ()
* feat(transformers): support also text generation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* embedded: set seed -1

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-01-23 23:07:31 +01:00
Ettore Di Giacinto
06cd9ef98d
feat(extra-backends): Improvements, adding mamba example ()
* feat(extra-backends): Improvements

vllm: add max_tokens, wire up stream event
mamba: fixups, adding examples for mamba-chat

* examples(mamba-chat): add

* docs: update
2024-01-20 17:56:08 +01:00
Ettore Di Giacinto
6ca4d38a01
docs/examples: enhancements ()
* docs: re-order sections

* fix references

* Add mixtral-instruct, tinyllama-chat, dolphin-2.5-mixtral-8x7b

* Fix link

* Minor corrections

* fix: models is a StringSlice, not a String

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP: switch docs theme

* content

* Fix GH link

* enhancements

* enhancements

* Fixed how to link

Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>

* fixups

* logo fix

* more fixups

* final touches

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>
Co-authored-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>
2024-01-18 19:41:08 +01:00
Ettore Di Giacinto
e19d7226f8
feat: more embedded models, coqui fixes, add model usage and description ()
* feat: add model descriptions and usage

* remove default model gallery

* models: add embeddings and tts

* docs: update table

* docs: updates

* images: cleanup pip cache after install

* images: always run apt-get clean

* ux: improve gRPC connection errors

* ux: improve some messages

* fix: fix coqui when no AudioPath is passed by

* embedded: add more models

* Add usage

* Reorder table
2024-01-08 00:37:02 +01:00
Ettore Di Giacinto
09e5d9007b
feat: embedded model configurations, add popular model examples, refactoring ()
* move downloader out

* separate startup functions for preloading configuration files

* docs: add popular model examples

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* shorteners

* Add llava

* Add mistral-openorca

* Better link to build section

* docs: update

* fixup

* Drop code dups

* Minor fixups

* Apply suggestions from code review

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

* ci: try to cache gRPC build during tests

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: do not build all images for tests, just necessary

* ci: cache gRPC also in release pipeline

* fixes

* Update model_preload_test.go

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-01-05 23:16:33 +01:00