llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-31 22:53:52 -04:00

Files

Shijie 37c746d687 llama : add Qwen support (#4281 )

* enable qwen to llama.cpp

* llama : do not GPU split bias tensors

---------

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

2023-12-01 20:16:31 +02:00

alpaca.txt

…

assistant.txt

2023-10-18 16:21:57 +03:00

chat-with-baichuan.txt

2023-09-14 12:32:10 -04:00

chat-with-bob.txt

2023-04-14 22:58:43 +03:00

chat-with-qwen.txt

2023-12-01 20:16:31 +02:00

chat-with-vicuna-v0.txt

…

chat-with-vicuna-v1.txt

…

chat.txt

…

dan-modified.txt

…

dan.txt

…

LLM-questions.txt

…

mnemonics.txt

2023-10-12 09:35:30 +03:00

parallel-questions.txt

…

reason-act.txt

…