HappyZ happyz
happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:59 -07:00
af4de844b2 Merge 0d701ad0b2d51308f39751159d4c454abccf4386 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 5 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:59 -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 5 commits »
happyz synced commits to refs/pull/6829/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:58 -07:00
44a6eda782 Merge b8aa13681ad73e396ca1174bf0524e0740119ab8 into ca36326020
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 4 commits »
happyz synced commits to refs/pull/6834/head at happyz/llama.cpp from mirror 2024-05-05 10:17:58 -07:00
f3f3aa8c94 ChatON:Initial go at vicuna chat template in meta.json
46171fad5c ChatON:chat template for OpenChat in meta.json initial go
5ab03b8ca7 ChatON: initial go at OrionStar Ai chat model template
13616422b5 SimpCfg: Cleanup the Note a bit to avoid some ambiguities
Compare 4 commits »
happyz synced commits to refs/pull/6828/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:58 -07:00
9270f17abe Merge 76a97c71874c976773e83c422c26b5f36fc28bcb 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 6 commits »
happyz synced commits to refs/pull/6811/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:57 -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/6810/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:57 -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 15 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:57 -07:00
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 4 commits »
happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:57 -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/6766/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:57 -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/6412/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:56 -07:00
137f8c5718 Merge 82aebcf0d989ca3736a5bd53885a857101430828 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 6 commits »
happyz synced commits to refs/pull/6413/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:56 -07:00
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)
842500144e gguf-split: add --no-tensor-first-split (#7072)
Compare 11 commits »
happyz synced commits to refs/pull/6408/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:56 -07:00
e90e8585ab Merge dc572071d33b7e029e2d406ade8470e2de91f617 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 13 commits »
happyz synced commits to refs/pull/5730/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:56 -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 master at happyz/llama.cpp from mirror 2024-05-05 10:17:56 -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 4 commits »
happyz synced and deleted reference refs/tags/refs/pull/7063/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:55 -07:00
happyz synced and deleted reference refs/tags/refs/pull/7034/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:55 -07:00
happyz synced and deleted reference refs/tags/refs/pull/7065/merge at happyz/llama.cpp from mirror 2024-05-05 10:17:55 -07:00
happyz synced commits to compilade/lazy-convert-hf at happyz/llama.cpp from mirror 2024-05-05 10:17:55 -07:00
bc78bf4cdb convert-hf : faster model parts loading
happyz synced new reference 0cc4m/vulkan-improvements to happyz/llama.cpp from mirror 2024-05-05 10:17:55 -07:00