a89427908d
Add custom kq scaling from Gemma2Attention
2024-06-29 10:17:33 -04:00
6f2464e3dd
Merge branch 'add-gemma2-soft-capping' of github.com:ggerganov/llama.cpp into add-gemma2-soft-capping
2024-06-29 01:11:17 -04:00
bb7159927d
Add default value for attention and final logit softcap value
2024-06-29 01:10:55 -04:00
3a2471811f
Update src/llama.cpp
...
Co-authored-by: slaren <slarengh@gmail.com >
2024-06-28 16:07:47 -04:00
f4424c150f
Disable flash attention for Gemma2
2024-06-28 16:00:20 -04:00
4d3f17b4ac
Add attention and final logit softcapping.
2024-06-28 15:42:19 -04:00
26a39bbd6b
Add MiniCPM, Deepseek V2 chat template + clean up llama_chat_apply_template_internal ( #8172 )
...
* tmp_contains
* minicpm chat template
* add DeepSeek Lite template
* change deepseek-lite to deepseek2
* correct code comment
* correct code from master branch
2024-06-28 15:11:44 +02:00
e57dc62057
llama: Add support for Gemma2ForCausalLM ( #8156 )
...
* Inference support for Gemma 2 model family
* Update convert-hf-to-gguf.py, constants, and tensor mappings
* cleanup
* format fix
* Fix special token vocab bug
* Don't add space prefix
* fix deleted lines
* Update src/llama.cpp
Co-authored-by: slaren <slarengh@gmail.com >
* Add model type names
* Add control vector
* Fix model type identification
---------
Co-authored-by: Andrei Betlen <abetlen@gmail.com >
Co-authored-by: slaren <slarengh@gmail.com >
2024-06-27 21:00:43 -07:00
6030c61281
Add Qwen2MoE 57B-A14B model identifier ( #8158 )
...
* Add Qwen2MoE 57B-A14B
* Add Qwen2MoE 57B-A14B
2024-06-27 16:27:41 +02:00
f675b20a3b
Added support for Viking pre-tokenizer ( #8135 )
...
Co-authored-by: kustaaya <kustaaya@protonmail.com >
2024-06-27 10:58:54 +02:00
911e35bb8b
llama : fix CodeLlama FIM token checks ( #8144 )
...
* account for space prefix character
* use find instead
2024-06-27 10:46:41 +03:00
f3f65429c4
llama : reorganize source code + improve CMake ( #8006 )
...
* scripts : update sync [no ci]
* files : relocate [no ci]
* ci : disable kompute build [no ci]
* cmake : fixes [no ci]
* server : fix mingw build
ggml-ci
* cmake : minor [no ci]
* cmake : link math library [no ci]
* cmake : build normal ggml library (not object library) [no ci]
* cmake : fix kompute build
ggml-ci
* make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE
ggml-ci
* move public backend headers to the public include directory (#8122 )
* move public backend headers to the public include directory
* nix test
* spm : fix metal header
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* scripts : fix sync paths [no ci]
* scripts : sync ggml-blas.h [no ci]
---------
Co-authored-by: slaren <slarengh@gmail.com >
2024-06-26 18:33:02 +03:00
Andrei Betlen