up version

minor update: thinking models

remove all deprecated finetuning code, fix ftune for qwen25

fix: more robust json parse for follow ups and locate

fix incorrect tag in release workflow

fix engine release cicd

modal size

remove refact-lsp and related logic (we dont use it) (smallcloudai#487)

* remove refact-lsp and related logic (we dont use it)

* remove lsp config and unneded hack

* remove lsp proxy

Bump the versions, new models support (smallcloudai#463)

* up the versions

* fixing starcoder2 flash sa

* integrate groq / cerebras to the self-hosting (smallcloudai#466)

* qwen2.5 models

* upd README.md

* a warning

* get rid of the autogptq models

* version 1.8.0

* version 1.8.0

* deprecated versions in the readme

* add completion support for the passthrough models

* add multiline_code_completion_default_model

* _select_default_lora_if_exists for multiline_code_completion_default_model
_add_results_for_passthrough_provider fix

* rm deepseek-coder-v2/16b/instruct
MAX_JOBS=8

* gpt-4 is unavailable

1.7.0 release updates (smallcloudai#454)

* remove deprecated models

* add new openai models

* up passthrough limit

* up litellm version

* up refact version to 1.7.0

* upgrade cython