HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/7158/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:51 -07:00
ebe8fda3fb Merge d3d32a6308 into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/7154/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:51 -07:00
5035613ce8 Merge d7359a389c into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/7107/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:50 -07:00
0db0192200 Merge d3286d6eca into d11afd6652
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 3 commits »
happyz synced commits to refs/pull/7117/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:50 -07:00
6ba53acf5b Merge bc924e0686 into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/7153/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:50 -07:00
48add6e5e6 Merge 9217f5ef36 into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 7 commits »
happyz synced commits to refs/pull/7150/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:50 -07:00
061ca33e91 Merge 113228ba23 into 4e3880978f
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 4 commits »
happyz synced commits to refs/pull/7083/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:49 -07:00
a4a71ae299 Merge 19d51bae2cd2ae85e559c60eee943d95dfc2eb42 into 8c570c9496
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 3 commits »
happyz synced commits to refs/pull/7058/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:49 -07:00
3ae225cc81 Merge 080b549958d5ff9f57b9677974e49309c6dec9fa into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
080b549958 Don't multiply embeddings with embedding_multiplier_scale as it happens in llama.cpp.
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
Compare 6 commits »
happyz synced commits to refs/pull/7058/head at happyz/llama.cpp from mirror 2024-05-10 06:38:49 -07:00
080b549958 Don't multiply embeddings with embedding_multiplier_scale as it happens in llama.cpp.
happyz synced commits to refs/pull/7096/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:49 -07:00
9b2fce401e Merge 17c1e23bed into f89fe2732c
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 3 commits »
happyz synced commits to refs/pull/7097/head at happyz/llama.cpp from mirror 2024-05-10 06:38:49 -07:00
9566de9a0d Merge branch 'master' into hkvc_chat_interactivespecials
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
Compare 10 commits »
happyz synced commits to refs/pull/7026/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:48 -07:00
d79b38cf35 Merge e7578d8c9d1f71388f3978211708888e5edea83e into d11afd6652
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
Compare 6 commits »
happyz synced commits to refs/pull/7020/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:48 -07:00
9cc60566ed Merge 9acc3ecf34 into 4e3880978f
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
Compare 6 commits »
happyz synced commits to refs/pull/6999/head at happyz/llama.cpp from mirror 2024-05-10 06:38:48 -07:00
95dabb1f03 convert-hf-to-gguf.py: fix flake8 warnings. Removed unused variable
1088626397 feature: Add ChatGLM3 chat template
86b5aeca1d bugfix: Omitted the colon, resulting in the failure of execution of convert-hf-to-gguf.py
72731db5f8 add chatglm3-6b model support
4e3880978f Fix memory bug in grammar parser (#7194)
Compare 11 commits »
happyz synced commits to refs/pull/6988/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:48 -07:00
842b1dc3be Merge a808370c58 into d11afd6652
d11afd6652 llava : fix moondream support (#7163)
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 4 commits »
happyz synced commits to refs/pull/6999/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:48 -07:00
2c33d9efaf Merge 95dabb1f033a9f7fa9616d55c2ae3f676ab602e4 into 25c6e82e7a
95dabb1f03 convert-hf-to-gguf.py: fix flake8 warnings. Removed unused variable
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
1088626397 feature: Add ChatGLM3 chat template
86b5aeca1d bugfix: Omitted the colon, resulting in the failure of execution of convert-hf-to-gguf.py
Compare 9 commits »
happyz synced commits to refs/pull/6934/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
17e500d474 Merge 50599208d6 into 8c570c9496
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
Compare 3 commits »
happyz synced commits to refs/pull/6919/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
e0eaeb5fff Merge a76fbcd050 into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/6942/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
47ebea6673 Merge 87a98a5b6d into 25c6e82e7a
25c6e82e7a llama : use n_vocab to differentiate between mistral 7B and llama3 8B (#7200)
4e3880978f Fix memory bug in grammar parser (#7194)
f89fe2732c Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd6652 llava : fix moondream support (#7163)
Compare 5 commits »
happyz synced commits to refs/pull/6951/merge at happyz/llama.cpp from mirror 2024-05-10 06:38:47 -07:00
c1cdc5bdfe Merge 2ff76f2458 into 8c570c9496
8c570c9496 Minor arithmetic improvement to mmvq wrapper kernel (#7172)
eaf4bd8b39 eval-callback : fix conversion to float (#7184)
befddd0f15 Vulkan Bugfixes and Improvements (#7084)
d46dbc76f8 readme : add scheduled server workflow status badge
Compare 7 commits »