HappyZ happyz
happyz synced commits to refs/pull/6781/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:59 -07:00
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
e8d35f47cb doc : add link to falcon (#6789)
2cca09d509 readme : add Fedora instructions (#6783)
89b0bf0d5d llava : use logger in llava-cli (#6797)
Compare 6 commits »
happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:59 -07:00
89b0bf0d5d llava : use logger in llava-cli (#6797)
b97bc3966e llama : support Llama 3 HF conversion (#6745)
ff5d21e608 switch to namedtuple, no need to dataclass
e5956f5bbe make script executable
Compare 5 commits »
happyz synced commits to refs/pull/6778/head at happyz/llama.cpp from mirror 2024-04-21 11:13:59 -07:00
ff5d21e608 switch to namedtuple, no need to dataclass
e5956f5bbe make script executable
Compare 2 commits »
happyz synced commits to refs/pull/6767/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:59 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6751/head at happyz/llama.cpp from mirror 2024-04-21 11:13:58 -07:00
16f8bba496 Merge branch 'master' into master
89b0bf0d5d llava : use logger in llava-cli (#6797)
b97bc3966e llama : support Llama 3 HF conversion (#6745)
b8109bc013 doc : server tests require llama to be built with curl enabled (#6788)
aed82f6837 common : try to fix Android CI (#6780)
Compare 10 commits »
happyz synced commits to refs/pull/6753/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:58 -07:00
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
e8d35f47cb doc : add link to falcon (#6789)
2cca09d509 readme : add Fedora instructions (#6783)
Compare 7 commits »
happyz synced commits to refs/pull/6757/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:58 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6766/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:58 -07:00
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
Compare 9 commits »
happyz synced commits to refs/pull/6707/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6745/head at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
c971ac034c llama : fix model type string for 8B model
23b8dd7dd4 llama : fix codegemma EOT token + add TODOs
7ab0939c0d convert : replacing EOS token is a hack
d0a4cc8ec8 llama : auto-detect more EOT tokens when missing in KV data
Compare 4 commits »
happyz synced commits to refs/pull/6739/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
e8d35f47cb doc : add link to falcon (#6789)
2cca09d509 readme : add Fedora instructions (#6783)
89b0bf0d5d llava : use logger in llava-cli (#6797)
Compare 6 commits »
happyz synced commits to refs/pull/6658/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
5cf8ccb191 llama : minor
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
Compare 11 commits »
happyz synced commits to refs/pull/6658/head at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
5cf8ccb191 llama : minor
happyz synced commits to refs/pull/6648/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:57 -07:00
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
Compare 9 commits »
happyz synced commits to refs/pull/6640/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
a9a2983630 Merge remote-tracking branch 'origin/master' into grammar-reps
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
Compare 11 commits »
happyz synced commits to refs/pull/6640/head at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
a9a2983630 Merge remote-tracking branch 'origin/master' into grammar-reps
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 32 commits »
happyz synced commits to refs/pull/6638/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6511/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
3c15639926 Merge a6f54dee3ca65ae1dbeab3f8c26c1d75a9609715 into b9cc76d87e
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
e8d35f47cb doc : add link to falcon (#6789)
Compare 8 commits »
happyz synced commits to refs/pull/6445/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
Compare 9 commits »
happyz synced commits to refs/pull/6644/merge at happyz/llama.cpp from mirror 2024-04-21 11:13:56 -07:00
5897bc83e9 Merge 1b988855dca2ced3850dbe40812707e639b1dbd6 into 7dbdba5690
7dbdba5690 llama : add llama-3 chat template (#6751)
c1386c936e gguf-py : add IQ1_M to GGML_QUANT_SIZES (#6761)
e8d35f47cb doc : add link to falcon (#6789)
2cca09d509 readme : add Fedora instructions (#6783)
Compare 7 commits »