diff options
| author | CausalLM <148736309+CausalLM@users.noreply.github.com> | 2023-12-02 02:17:06 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-12-01 20:17:06 +0200 |
| commit | 03562f3a86d6706eea9f4fc09b532946c191b34e (patch) | |
| tree | 709378616d9e23c4fb098dc61c7659b32e8740a4 /examples/tokenize | |
| parent | 37c746d687d877bc11803e96b4dc5f378b83c0a0 (diff) | |
llama : support attention bias on LLaMA architecture (#4283)
* Support attention_bias on LLaMA architecture
QKVO bias, should fix InternLM (https://github.com/ggerganov/llama.cpp/issues/3133) and works for LLaMAfied Qwen models (https://github.com/ggerganov/llama.cpp/pull/3743#issuecomment-1825923608).
* check existence of qkvo bias while loading llama models
Tested on LLaMA2, CUDA and CPU.
* Update llama.cpp
Diffstat (limited to 'examples/tokenize')
0 files changed, 0 insertions, 0 deletions