HappyZ happyz
happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:04 -07:00
1cc84b2d6d Merge 0d701ad0b2d51308f39751159d4c454abccf4386 into 842500144e
842500144e gguf-split: add --no-tensor-first-split (#7072)
cf768b7e71 Tidy Android Instructions README.md (#7016)
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
Compare 6 commits »
happyz synced commits to refs/pull/6891/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:04 -07:00
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 4 commits »
happyz synced commits to refs/pull/6965/head at happyz/llama.cpp from mirror 2024-05-04 10:18:04 -07:00
798b576c06 Merge remote-tracking branch 'upstream/master' into gg/bpe-preprocess
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
a2ac89d6ef convert.py : add python logging instead of print() (#6511)
433def286e llama : rename ctx to user_data in progress_callback (#7045)
Compare 35 commits »
happyz synced commits to refs/pull/6869/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
73cc68ecb2 Merge cf9dca34cbd02c89fb3f3c46e85da817fe89744b into 92139b90af
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
a2ac89d6ef convert.py : add python logging instead of print() (#6511)
433def286e llama : rename ctx to user_data in progress_callback (#7045)
Compare 4 commits »
happyz synced commits to refs/pull/6840/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
6a2b25e37c Merge c34c47237148ba264a4d1ac75d1ecc70c7952589 into fcd84a0f5a
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 4 commits »
happyz synced commits to refs/pull/6829/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
06a191b7c8 Merge b8aa13681ad73e396ca1174bf0524e0740119ab8 into 03fb8a002d
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 3 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
cf768b7e71 Tidy Android Instructions README.md (#7016)
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 5 commits »
happyz synced commits to refs/pull/6834/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
87c138804f Merge 2ac7fca47314b50a6c3628ab3e74e58eccb120db into fcd84a0f5a
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
2ac7fca473 SimpCfg:MultiPart keys wrt get_vector
d92087cfa8 SimpCfg:MultiPart keys wrt get_value etal
a7a90b411a SimpCfg: General MultiPart support, KeyParts not Key wrt SetValue
Compare 167 commits »
happyz synced commits to refs/pull/6834/head at happyz/llama.cpp from mirror 2024-05-04 10:18:03 -07:00
2ac7fca473 SimpCfg:MultiPart keys wrt get_vector
d92087cfa8 SimpCfg:MultiPart keys wrt get_value etal
a7a90b411a SimpCfg: General MultiPart support, KeyParts not Key wrt SetValue
32c82d54f7 SimpCfg: Use to_str instead of using stringstream directly
d162f13bba ChatON:Update meta.json wrt command-r models
Compare 182 commits »
happyz synced commits to refs/pull/6811/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:02 -07:00
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 3 commits »
happyz synced commits to refs/pull/6766/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:02 -07:00
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 2 commits »
happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:02 -07:00
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
a2ac89d6ef convert.py : add python logging instead of print() (#6511)
433def286e llama : rename ctx to user_data in progress_callback (#7045)
Compare 5 commits »
happyz synced commits to refs/pull/6822/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:02 -07:00
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 3 commits »
happyz synced commits to refs/pull/6828/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:02 -07:00
b618f78856 Merge 76a97c71874c976773e83c422c26b5f36fc28bcb into cf768b7e71
cf768b7e71 Tidy Android Instructions README.md (#7016)
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 5 commits »
happyz synced commits to refs/pull/6371/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 3 commits »
happyz synced commits to refs/pull/6412/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
1793959913 Merge 82aebcf0d989ca3736a5bd53885a857101430828 into cf768b7e71
cf768b7e71 Tidy Android Instructions README.md (#7016)
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 5 commits »
happyz synced and deleted reference refs/tags/refs/pull/7064/merge at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
happyz synced commits to compilade/convert-hf-refactor at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
f2099c50ab convert-hf : align the message logged for converted tensors
happyz synced commits to compilade/lazy-convert-hf at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
b2de1b3913 convert-hf : flake8 doesn't like lowercase L as a variable name
866865e711 convert-hf : save memory with lazy evaluation
f2099c50ab convert-hf : align the message logged for converted tensors
Compare 3 commits »
happyz synced commits to master at happyz/llama.cpp from mirror 2024-05-04 10:18:01 -07:00
842500144e gguf-split: add --no-tensor-first-split (#7072)
cf768b7e71 Tidy Android Instructions README.md (#7016)
fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064)
03fb8a002d If first token generated from the server is the stop word the server will crash (#7038)
92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
Compare 5 commits »