ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
llama.cpp/src
History
Olivier Chafik c7f460ab88
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none (#11607) 
* extract & return thoughts in reasoning_content field (unless --reasoning-format) for DeepSeek R1 & Command R7B

* tool-calls: add deepseek r1 template (models/templates/llama-cpp-deepseek-r1.jinja) + hackommodate broken official template

* tool-calls: accommodate variety of wrong tool call opening tags both R1 Qwen 32B and 7B distills like to spit out

* server/oai: ensure content is null when there are tool calls, and reasoning_content appears before content for readability

* tool-calls: add DeepSeek R1 Qwen distills to server/README.md & server tests

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-02-13 10:05:16 +00:00
..
CMakeLists.txt Add Jinja template support (#11016) 2025-01-21 13:18:51 +00:00
llama-adapter.cpp llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-adapter.h llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-arch.cpp llama : add support for GLM-Edge and GLM-Edge-V series models (#10573) 2025-02-02 09:48:46 +02:00
llama-arch.h Add Jinja template support (#11016) 2025-01-21 13:18:51 +00:00
llama-batch.cpp llama : refactor src/llama.cpp (#10902) 2025-01-03 10:18:53 +02:00
llama-batch.h llama : refactor src/llama.cpp (#10902) 2025-01-03 10:18:53 +02:00
llama-chat.cpp llama : add support for GLM-Edge and GLM-Edge-V series models (#10573) 2025-02-02 09:48:46 +02:00
llama-chat.h llama : add support for GLM-Edge and GLM-Edge-V series models (#10573) 2025-02-02 09:48:46 +02:00
llama-context.cpp llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-context.h llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-cparams.cpp llama : refactor src/llama.cpp (#10902) 2025-01-03 10:18:53 +02:00
llama-cparams.h llama : refactor src/llama.cpp (#10902) 2025-01-03 10:18:53 +02:00
llama-grammar.cpp server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none (#11607) 2025-02-13 10:05:16 +00:00
llama-grammar.h llama : fix typo in llama-grammar.h [no ci] (#11816) 2025-02-12 09:40:01 +02:00
llama-hparams.cpp llama: add support for QRWKV6 model architecture (#11001) 2025-01-10 09:58:08 +08:00
llama-hparams.h llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-impl.cpp GGUF: C++ refactor, backend support, misc fixes (#11030) 2025-01-07 18:01:58 +01:00
llama-impl.h cleanup: fix compile warnings associated with gnu_printf (#11811) 2025-02-12 10:06:53 -04:00
llama-kv-cache.cpp llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-kv-cache.h llama : update llama_decode_internal ref [no ci] (#11840) 2025-02-13 08:07:51 +02:00
llama-mmap.cpp mmap: add include for cerrno (#11296) 2025-01-20 16:02:43 +02:00
llama-mmap.h llama-mmap: fix missing include (#11796) 2025-02-10 20:58:18 +02:00
llama-model-loader.cpp llama : minor fixes for up llama load model speed (#11448) 2025-01-27 14:42:09 +01:00
llama-model-loader.h llama : add llama_model_load_from_splits (#11255) 2025-01-16 13:54:08 +01:00
llama-model.cpp cont : fix mmap flag print (#11699) 2025-02-08 16:49:38 +02:00
llama-model.h rpc : early register backend devices (#11262) 2025-01-17 10:57:09 +02:00
llama-quant.cpp llama : add llama_model_load_from_splits (#11255) 2025-01-16 13:54:08 +01:00
llama-quant.h llama : refactor src/llama.cpp (#10902) 2025-01-03 10:18:53 +02:00
llama-sampling.cpp sampling: add Top-nσ sampler (#11223) 2025-02-13 08:45:57 +02:00
llama-sampling.h llama : add llama_vocab, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama-vocab.cpp vocab : correctly identify LF token for GPT-2 style BPE tokenizer (#11496) 2025-01-30 12:10:59 +02:00
llama-vocab.h llama : remove notion of CLS token (#11064) 2025-01-12 12:15:53 +02:00
llama.cpp cont : fix mmap flag print (#11699) 2025-02-08 16:49:38 +02:00
unicode-data.cpp server : better security control for public deployments (#9776) 2024-10-08 13:27:04 +02:00
unicode-data.h llama : reduce compile time and binary size (#9712) 2024-10-02 15:49:55 +02:00
unicode.cpp vocab : ignore invalid UTF-8 input in the BPE tokenizer (#11729) 2025-02-07 15:55:47 +02:00
unicode.h unicode : improve naming style (#10838) 2024-12-16 12:31:45 +02:00