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

..

build-info.sh

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

check-requirements.sh

py : type-check all Python scripts with Pyright (#8341)

2024-07-07 15:04:39 -04:00

ci-run.sh

ci : add model tests + script wrapper (#4586)

2024-01-26 14:18:00 +02:00

compare-commits.sh

scripts : change build path to "build-bench" for compare-commits.sh (#10836)

2024-12-15 18:44:47 +02:00

compare-llama-bench.py

ggml : more perfo with llamafile tinyblas on x86_64 (#10714)

2024-12-24 18:54:49 +01:00

debug-test.sh

scripts : fix spelling typo in messages and comments (#9782)

2024-10-08 09:19:53 +03:00

fetch_server_test_models.py

Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)

2025-01-30 19:13:58 +00:00

gen-authors.sh

license : update copyright notice + add AUTHORS (#6405)

2024-04-09 09:23:19 +03:00

gen-unicode-data.py

py : type-check all Python scripts with Pyright (#8341)

2024-07-07 15:04:39 -04:00

get_chat_template.py

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

get-flags.mk

build : pass all warning flags to nvcc via -Xcompiler (#5570)

2024-02-18 16:21:52 -05:00

get-hellaswag.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

get-pg.sh

scripts : improve get-pg.sh (#4838)

2024-01-09 19:21:13 +02:00

get-wikitext-2.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

get-wikitext-103.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

get-winogrande.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

hf.sh

scripts : restore hf.sh (#11288)

2025-01-18 13:18:32 +02:00

install-oneapi.bat

support SYCL backend windows build (#5208)

2024-01-31 08:08:07 +05:30

qnt-all.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

run-all-perf.sh

scripts : add pipefail

2023-08-29 10:50:30 +03:00

run-all-ppl.sh

build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)

2024-06-13 00:41:52 +01:00

sync-ggml-am.sh

scripts : sync gguf (cont)

2025-01-14 09:40:52 +02:00

sync-ggml.last

sync : ggml

2025-02-12 21:46:02 +02:00

sync-ggml.sh

scripts : sync gguf

2025-01-14 09:36:58 +02:00

verify-checksum-models.py

convert.py : add python logging instead of print() (#6511)

2024-05-03 22:36:41 +03:00

xxd.cmake

build: generate hex dump of server assets during build (#6661)

2024-04-21 18:48:53 +01:00