2b131ad1d2
refactor: handle max output length in StopCondition ( #910 )
...
* refactor: handle max output length in StopCondition
* trim stop words
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-28 16:57:16 +08:00
a7202318b1
refactor: make language optional in TextGenerationOptions ( #897 )
...
* refactor: make language optional in TextGenerationOptions
* [autofix.ci] apply automated fixes
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2023-11-26 11:17:31 +08:00
296342efd8
refactor: use llama.cpp tokenizer ( #683 )
...
* refactor: switch to llama.cpp tokenizer to simplify implementation
* refactor: remove tokenizer dependency from tabby
* refactor: renaming decoding to stop condition
* refactor: remove tokenizer dependency
* refactor: remove submodule
* chore: update formatting
* move tokenization to c++
2023-10-31 22:16:09 +00:00
99a7053b6f
refactor: extract language configuration into individual toml file ( #564 )
...
* refactor: extract language configuration into individual toml file
* feat: add golang language configuration (#565 )
2023-10-16 00:24:44 +00:00
8c09f75360
refactor: extract language related data into languages.rs ( #518 )
...
* refactor: extract language related data into languages.rs
* fix
* cleanup index
* fix
* further sanitize
* add a score threshold
2023-10-07 01:40:21 +00:00
fd2a1ab865
fix: switch back to regex based implementation for stop words ( #513 )
2023-10-06 09:04:37 +00:00
ce20bd6154
refactor: use RegexSet for cleaer stop regex construction ( #499 )
...
* fix: add a regression test cased for stop words regex matching
* refactor: use RegexSet for cleaer stop regex construction
2023-10-02 23:21:51 +00:00
f05dd3a2f6
refactor: cleanup chat api make it message oriented ( #497 )
...
* refactor: refactor into /chat/completions api
* Revert "feat: support request level stop words (#492 )"
This reverts commit 0d6840e372
2023-10-02 15:39:15 +00:00
0d6840e372
feat: support request level stop words ( #492 )
2023-09-29 18:21:57 +00:00
486e507079
fix: correct Decoding behavior in incremental manner ( #491 )
...
* feat: implement IncrementalDecoding
* refactor: use IncrementalDecoding for ctranslate2
* refactor: rename StopWords to DecodingFactory
* refactor: move decoding logic to tabby-inference
* feat: optimize decoding range
* cleanup
2023-09-29 13:06:47 +00:00
44f013f26e
feat: add /generate and /generate_streaming ( #482 )
...
* feat: add generate_stream interface
* extract engine::create_engine
* feat add generate::generate
* support streaming in llama.cpp
* support streaming in ctranslate2
* update
* fix formatting
* refactor: extract helpers functions
2023-09-28 17:20:50 +00:00
17397c8c8c
feat: add http api bindings ( #410 )
...
* feat: add http-api-bindings
* feat: add http-api-bindings
* hand max_input_length
* rename
* update
* update
* add examples/simple.rs
* update
* add default value for stop words
* update
* fix lint
* update
2023-09-09 03:59:42 +00:00
87b6b34120
feat: implement input truncation with options.max_input_length ( #415 )
2023-09-08 10:01:03 +00:00
3573d4378e
feat: llama.cpp for metal support [TAB-146] ( #391 )
...
* feat: init commit adding llama-cpp-bindings
* add llama.cpp submodule
* add LlamaEngine to hold llama context / llama model
* add cxxbridge
* add basic greedy sampling
* move files
* make compile success
* connect TextGeneration with LlamaEngine
* experimental support llama.cpp
* add metal device
* add Accelerate
* fix namespace for llama-cpp-bindings
* fix lint
* move stepping logic to rust
* add stop words package
* use stop-words in ctranslate2-bindings
* use raw string for regex
* use Arc<Tokenizer> for sharing tokenizers
* refactor: remove useless stop_words_encoding_offset
* switch to tokenizers 0.13.4-rc.3
* fix lints in cpp
* simplify implementation of greedy decoding
* feat: split metal feature for llama backend
* add ci
* update ci
* build tabby bin in ci build
2023-09-03 09:59:07 +08:00
b8308b7118
refactor: extract TextGeneration trait ( #324 )
...
* add tabby-inference
* extract TextGeneration trait
* format
* Rename TextInferenceEngine to CTranslate2Engine
2023-08-02 06:12:51 +00:00
Meng Zhang