Olivier Chafik
|
f5cd27b71d
`server`: streaming of tool calls and thoughts when `--jinja` is on (#12379)
|
7 месяцев назад |
Olivier Chafik
|
aa48e373f2
`server`: inject date_string in llama 3.x template + fix date for firefunction v2 (#12802)
|
8 месяцев назад |
Xuan-Son Nguyen
|
8c83449cb7
server : (webui) revamp the input area, plus many small UI improvements (#13365)
|
8 месяцев назад |
Olivier Chafik
|
b6930ebc42
`tool-call`: fix non-tool-calling grammar crashes w/ Qwen / Hermes 2 templates (#12900)
|
9 месяцев назад |
Olivier Chafik
|
4e39a3c332
`server`: extract <think> tags from qwq outputs (#12297)
|
10 месяцев назад |
Olivier Chafik
|
87c2630546
allow missing content in message if tool_calls provided (#12293)
|
10 месяцев назад |
Olivier Chafik
|
669912d9a5
`tool-call`: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)
|
10 месяцев назад |
Olivier Chafik
|
63e489c025
tool-call: refactor common chat / tool-call api (+ tests / fixes) (#11900)
|
11 месяцев назад |
Olivier Chafik
|
f355229692
server: fix type promotion typo causing crashes w/ --jinja w/o tools (#11880)
|
11 месяцев назад |
Olivier Chafik
|
c7f460ab88
`server`: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless `--reasoning-format none` (#11607)
|
11 месяцев назад |
Olivier Chafik
|
9f4cc8f8d3
`sync`: minja (#11641)
|
11 месяцев назад |
Olivier Chafik
|
db288b60cb
`tool-call`: command r7b fix for normal responses (#11608)
|
11 месяцев назад |
Olivier Chafik
|
bfcce4d693
`tool-call`: support Command R7B (+ return tool_plan "thoughts" in API) (#11585)
|
11 месяцев назад |
Olivier Chafik
|
a83f528688
`tool-call`: fix llama 3.x and functionary 3.2, play nice w/ pydantic_ai package, update readme (#11539)
|
11 месяцев назад |
Olivier Chafik
|
8b576b6c55
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)
|
11 месяцев назад |