HappyZ happyz
happyz synced new reference dependabot/go_modules/google.golang.org/protobuf-1.34.1 to happyz/memos from mirror 2024-05-06 10:17:40 -07:00
happyz synced commits to dependabot/go_modules/google.golang.org/protobuf-1.34.1 at happyz/memos from mirror 2024-05-06 10:17:40 -07:00
happyz synced commits to dependabot/go_modules/golang.org/x/oauth2-0.20.0 at happyz/memos from mirror 2024-05-06 10:17:39 -07:00
happyz synced commits to dependabot/go_modules/golang.org/x/crypto-0.23.0 at happyz/memos from mirror 2024-05-06 10:17:39 -07:00
happyz synced new reference dependabot/go_modules/golang.org/x/crypto-0.23.0 to happyz/memos from mirror 2024-05-06 10:17:39 -07:00
happyz synced commits to refs/pull/7077/head at happyz/llama.cpp from mirror 2024-05-05 22:18:03 -07:00
7f0b8dd495 Organized required packages per build type
8ae63953fe re-word for clarity
Compare 2 commits »
happyz synced commits to refs/pull/7075/head at happyz/llama.cpp from mirror 2024-05-05 22:18:02 -07:00
62303e7f77 convert-hf : minor changes for consistency
happyz synced commits to refs/pull/7027/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:02 -07:00
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
Compare 4 commits »
happyz synced commits to refs/pull/7041/head at happyz/llama.cpp from mirror 2024-05-05 22:18:02 -07:00
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
6fbd432211 py : logging and flake8 suppression refactoring (#7081)
Compare 12 commits »
happyz synced commits to refs/pull/7075/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:02 -07:00
62303e7f77 convert-hf : minor changes for consistency
Compare 2 commits »
happyz synced commits to refs/pull/7013/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:01 -07:00
5f4d9dbe4d Merge branch 'ggerganov:master' into master
Compare 2 commits »
happyz synced commits to refs/pull/7013/head at happyz/llama.cpp from mirror 2024-05-05 22:18:01 -07:00
5f4d9dbe4d Merge branch 'ggerganov:master' into master
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
Compare 21 commits »
happyz synced commits to refs/pull/6999/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:01 -07:00
1d420c308c Merge 9a8db6b2b4b54d1da178fd7c961839276fd98e52 into 628b299106
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
Compare 11 commits »
happyz synced commits to refs/pull/6988/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:01 -07:00
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
Compare 6 commits »
happyz synced commits to refs/pull/7026/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:01 -07:00
26252e86ce Merge e7578d8c9d1f71388f3978211708888e5edea83e into 628b299106
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
Compare 3 commits »
happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:00 -07:00
d0f853bbde Merge e2dcf468dc40866ff4468bdc0b41d61bbaf5caec into 628b299106
e2dcf468dc Merge branch 'master' into MMThreadingPerfChange
Compare 2 commits »
happyz synced commits to refs/pull/6942/head at happyz/llama.cpp from mirror 2024-05-05 22:18:00 -07:00
b7c612088f tentative push of convert-hf-to-gguf support
happyz synced commits to refs/pull/6915/head at happyz/llama.cpp from mirror 2024-05-05 22:18:00 -07:00
e2dcf468dc Merge branch 'master' into MMThreadingPerfChange
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
Compare 44 commits »
happyz synced commits to refs/pull/6934/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:00 -07:00
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
8f8acc8683 Disable benchmark on forked repo (#7034)
ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065)
889bdd7686 command-r : add BPE pre-tokenization (#7063)
Compare 6 commits »
happyz synced commits to refs/pull/6910/merge at happyz/llama.cpp from mirror 2024-05-05 22:18:00 -07:00
69432502cd add OLMo to pre-tokenizer function
da41960dbe Merge branch 'update-olmo-tokenizer' into fix-olmo-conversion
c80768392a add OLMo to pre-tokenizer generation script
628b299106 Adding support for the --numa argument for llama-bench. (#7080)
Compare 16 commits »