Meng Zhang
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
Meng Zhang
f37840566b
feat: upgrade llama.cpp ( #645 )
...
* feat: upgrade llama.cpp
* update download files
* update changelog
* Update CHANGELOG.md
* Update CHANGELOG.md
2023-10-27 12:18:46 -07:00
Meng Zhang
6306bb3f01
fix: if local file doens't exist, local_cache_key should be cleared ( #501 )
...
* fix: if local file doens't exist, local_cache_key should be cleared
* fix
2023-10-02 23:48:35 +00:00
Meng Zhang
63612d5a67
fix(tabby-download): even when prefer_local_file is set to true, we should still check for remote (if network is avaialble), to see if a file should be upgraded ( #500 )
2023-10-02 23:09:57 +00:00
Meng Zhang
d42942c379
feat: support ModelScope for model registry downloading ( #477 )
...
* feat: update cache info file after each file got downloaded
* refactor: extract Downloader for model downloading logic
* refactor: extract HuggingFaceRegistry
* refactor: extract serde_json to workspace dependency
* feat: add ModelScopeRegistry
* refactor: extract registry to its sub dir.
* feat: add scripts to mirror hf model to modelscope
2023-09-26 11:52:11 -07:00
Meng Zhang
e780031ed6
feat: add ggml fp16 / q8_0 files ( #407 )
...
* feat: add ggml fp16 / q8_0 files
* add q8_0.gguf to optional download files
* add download options to split ctranslate2 files and ggml files
2023-09-06 17:12:29 +00:00
Meng Zhang
6a50902ca7
fix: support ctranslate2 rev7 vocab files (.json) ( #327 )
2023-08-02 13:36:31 +00:00
Meng Zhang
57c811b30f
fix: improve download logging ( #325 )
...
* Suggest use `-it` so docker run generate progress bar of downloading information properly
* add info! log for model download
2023-08-02 06:30:35 +00:00
Meng Zhang
e822d1857f
fix: add retry strategy in tabby download ( #285 )
2023-07-09 05:18:19 +00:00
Meng Zhang
9abf1a7521
fix: optional file should be put in cache key to avoid internet access when prefer_local_files = true ( #241 )
...
* feat: when file is 404, cache as NotFound
* explicitly mark optional file
* refactor
2023-06-15 04:13:52 +00:00
Meng Zhang
eecdde0269
fix: vocabulary.txt / shared_vocabulary.txt should be optional ( #225 )
2023-06-09 06:49:09 +00:00
Meng Zhang
1aaf29c968
docs: switch openapi docs ( #215 )
...
* update openapi
* update
* fix: shared_vocabulary is not a required file
* docs: improve docs
2023-06-07 01:58:05 -07:00
Meng Zhang
4cb672ec39
feat: improve error handling and messages [TAB-58] ( #213 )
...
* add fatal macro
* switch expect to fatal
* improve error handling of serve
* improve error handling on download module
* improve error handling in scheduler
* improve error handling
* fmt
* fmt
2023-06-07 02:02:58 +00:00
Meng Zhang
272dde9769
refactor: rust nightly format ( #197 )
...
* chore: turn on group format
* turn on nightly fmt
2023-06-05 14:17:07 -07:00
Meng Zhang
e8a33312bb
refactor: extract download into tabby-download ( #195 )
...
* refactor: extract download into tabby-download
* remove unused deps
2023-06-05 18:40:24 +00:00