Block a user
root
synced commits to refs/pull/9338/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
c35fbd6b2c
Merge
afb016c138
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
8db003a19d
py : support converting local models (#7547)
0996c5597f
llava : correct args for minicpmv-cli (#9429)
5bb2c5dbd2
files : remove accidentally added
lora_test
submodule (#9430)
root
synced commits to refs/pull/9339/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
aa91191a27
Merge
b7d6eb0e2c
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
8db003a19d
py : support converting local models (#7547)
0996c5597f
llava : correct args for minicpmv-cli (#9429)
5bb2c5dbd2
files : remove accidentally added
lora_test
submodule (#9430)
root
synced commits to refs/pull/9355/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
38eeb2fbe9
Merge
f42de2426e
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9396/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
5f74a32541
Merge
141dd55e53
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9397/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
a31b2d2cca
Merge
94596be679
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9400/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
59cee40998
Merge
2d79a7077c
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9403/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
e10c4f0ffd
Merge
1e8646b3e8
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9406/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
e19bc89c4e
Merge
03b52bf908
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9407/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
fe91675b07
Merge
adf3bce13b
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9408/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
534c49c536
Merge
ee154457dd
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
2ed6a172ca
fix(convert_hf_to_gguf): Use LlamaModel as base for GraniteModel
e8a1073240
fix(llama.cpp): Determine granite language 3b instruct by vocab size
2ec91ee86b
feat(llama.cpp): First pass at full port of granite deviations from llama
009a2b4aae
feat(llama.cpp): Add config parsing for Granite multiplier params
7152e2ce31
feat(convert_hf_to_gguf): Add registration and param setup for Granite
root
synced commits to refs/pull/9412/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
2022310d80
Merge
2ed6a172ca
into 1b28061400
2ed6a172ca
fix(convert_hf_to_gguf): Use LlamaModel as base for GraniteModel
e8a1073240
fix(llama.cpp): Determine granite language 3b instruct by vocab size
2ec91ee86b
feat(llama.cpp): First pass at full port of granite deviations from llama
009a2b4aae
feat(llama.cpp): Add config parsing for Granite multiplier params
3653fede2b
log : try to fix thread sanitizer CI
f029947491
log : fix UBs
b89733ecd7
llava : add missing header [no ci]
938909394f
llava : remove common includes [no ci]
b2a7bbdd48
build : add headers
root
synced commits to refs/pull/9418/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
d461d0b665
Merge
3653fede2b
into 1b28061400
3653fede2b
log : try to fix thread sanitizer CI
f029947491
log : fix UBs
b89733ecd7
llava : add missing header [no ci]
938909394f
llava : remove common includes [no ci]
root
synced commits to refs/pull/9424/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
bd3a1228f5
Merge
fb24e846a9
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced commits to refs/pull/9428/merge at root/llama.cpp from mirror
2024-09-12 00:06:18 +00:00
e0e860dab0
Merge
691b0f94fa
into 1b28061400
1b28061400
llama : skip token bounds check when evaluating embeddings (#9437)
root
synced and deleted reference 2024-09-12 00:06:17 +00:00
refs/tags/refs/pull/9434/merge
at root/llama.cpp from mirror