Alex O'Connell
|
ab32942006
|
more fixes for llm API
|
2024-06-06 23:08:04 -04:00 |
|
Alex O'Connell
|
36e29bedf0
|
add an LLM API to support the existing models
|
2024-06-06 22:40:59 -04:00 |
|
Alex O'Connell
|
b10ede765e
|
update readme and todo
|
2024-06-05 23:37:05 -04:00 |
|
Alex O'Connell
|
b50904d73b
|
handle multi-turn tool models
|
2024-06-02 22:13:54 -04:00 |
|
Alex O'Connell
|
dbed6de6cd
|
Finish renaming stuff
|
2024-06-02 13:02:57 -04:00 |
|
Alex O'Connell
|
00d002d9c0
|
make tool formats work + dynamic quantization detection from HF
|
2024-06-02 12:25:26 -04:00 |
|
Alex O'Connell
|
8546767310
|
version with working ICL using the new APIs
|
2024-06-01 23:06:42 -04:00 |
|
Alex O'Connell
|
367607b14f
|
more rewrite work for new LLM API
|
2024-05-25 21:24:45 -04:00 |
|
Alex O'Connell
|
8a28dd61ad
|
update naming and start implementing new LLM API support
|
2024-05-25 17:12:58 -04:00 |
|
Alex O'Connell
|
9cacc4d78e
|
Merge branch 'main' into develop
|
2024-05-08 21:05:02 -04:00 |
|
Alex O'Connell
|
d64f3a25f6
|
Merge pull request #142 from acon96/release/v0.2.17
Release v0.2.17
v0.2.17
|
2024-05-08 21:04:36 -04:00 |
|
Alex O'Connell
|
105f09ba2c
|
Release v0.2.17
|
2024-05-08 21:00:06 -04:00 |
|
Alex O'Connell
|
179e794283
|
add cmdline arguments to translate script + add defaults for command r
|
2024-05-08 20:50:25 -04:00 |
|
Stefan Daniel Schwarz
|
7404b6b36c
|
command-r prompt template (#141)
|
2024-05-07 22:33:47 +00:00 |
|
Alex O'Connell
|
ca4c27232e
|
tweak build configurations
|
2024-05-06 21:55:14 -04:00 |
|
Alex O'Connell
|
582207290f
|
re-do detection again to force it to default to -noavx if features aren't found
|
2024-05-04 22:24:23 -04:00 |
|
Alex O'Connell
|
1786c19728
|
Merge branch 'main' into develop
|
2024-05-04 13:38:17 -04:00 |
|
Alex O'Connell
|
0cb361c305
|
Merge pull request #138 from acon96/release/v0.2.16
Release v0.2.16
v0.2.16
|
2024-05-04 13:37:44 -04:00 |
|
Alex O'Connell
|
6f2ce8828e
|
Release v0.2.16
|
2024-05-04 13:28:51 -04:00 |
|
Alex O'Connell
|
dc79b2615e
|
pin dependencies + fix huggingface import error after HA updates
|
2024-05-04 13:23:42 -04:00 |
|
Alex O'Connell
|
026a95d576
|
add prompt format for phi-3
|
2024-05-04 12:59:48 -04:00 |
|
Alex O'Connell
|
d3f9aa81e5
|
Merge branch 'main' into develop
|
2024-05-04 07:37:22 -04:00 |
|
Alex O'Connell
|
687f49f2c3
|
Merge pull request #136 from acon96/release/v0.2.15
Release v0.2.15
v0.2.15
|
2024-05-04 07:36:44 -04:00 |
|
Alex O'Connell
|
26be7d7dcd
|
fix other error message
|
2024-05-04 07:36:15 -04:00 |
|
Alex O'Connell
|
9eacd3edb2
|
Release v0.2.15
|
2024-05-04 07:33:39 -04:00 |
|
Alex O'Connell
|
f95793433e
|
one other tweak to timeout warning
|
2024-05-04 07:31:50 -04:00 |
|
Alex O'Connell
|
0bd969f851
|
re-enable armhf builds
|
2024-05-04 07:30:53 -04:00 |
|
Alex O'Connell
|
9b9de48ad4
|
fix tests
|
2024-05-03 22:52:34 -04:00 |
|
Alex O'Connell
|
cdd7e8415a
|
hook up flash attention
|
2024-05-02 23:05:43 -04:00 |
|
Alex O'Connell
|
7a649546ff
|
fix multiprocessing error
|
2024-05-02 22:56:45 -04:00 |
|
Alex O'Connell
|
4b9f9ed2fa
|
properly validate install if we are re-installing
|
2024-05-02 22:46:59 -04:00 |
|
Alex O'Connell
|
0676c8f41a
|
better messaging on timeout
|
2024-05-02 22:34:43 -04:00 |
|
Alex O'Connell
|
70e1fe3946
|
Merge branch 'main' into develop
|
2024-05-02 21:59:34 -04:00 |
|
Alex O'Connell
|
3e30ac9378
|
fix manifest
v0.2.14
|
2024-05-02 21:59:18 -04:00 |
|
Alex O'Connell
|
9ed95dd987
|
Merge pull request #132 from acon96/release/v0.2.14
Release v0.2.14
|
2024-05-02 21:55:06 -04:00 |
|
Alex O'Connell
|
875547d2e2
|
Release v0.2.14
|
2024-05-02 21:53:14 -04:00 |
|
Alex O'Connell
|
1cbba9e0d0
|
fix detection logic
|
2024-05-02 21:45:53 -04:00 |
|
Alex O'Connell
|
6e849f19bb
|
avoid crashing home assistant if possible
|
2024-05-02 21:20:13 -04:00 |
|
Alex O'Connell
|
a422b2c719
|
detect all required features for default build + disable f16c on noavx build
|
2024-05-02 20:52:14 -04:00 |
|
Alex O'Connell
|
465f6b12f6
|
Merge branch 'main' into develop
|
2024-05-02 20:46:57 -04:00 |
|
Alex O'Connell
|
f301e5cf45
|
fix avx2 detection
|
2024-04-25 20:23:23 -04:00 |
|
Alex O'Connell
|
4458348302
|
support evaluating models from HF with ICL
|
2024-04-25 00:20:50 -04:00 |
|
Alex O'Connell
|
e6527e81b9
|
Merge branch 'main' into develop
|
2024-04-24 21:44:25 -04:00 |
|
Alex O'Connell
|
bcb10adc4b
|
disable armhf builds for now
v0.2.13
|
2024-04-24 21:42:54 -04:00 |
|
Alex O'Connell
|
d6b1aa0357
|
Merge pull request #127 from acon96/release/v0.2.13
Release v0.2.13
|
2024-04-24 21:33:12 -04:00 |
|
Alex O'Connell
|
d3f0ebd1cb
|
remove languages bit for now
|
2024-04-24 21:30:25 -04:00 |
|
Alex O'Connell
|
27d64f4c87
|
default to noavx if you can't detect cpu features
|
2024-04-24 21:28:32 -04:00 |
|
Alex O'Connell
|
8d6116d4c3
|
bump version numbers
|
2024-04-24 21:25:27 -04:00 |
|
Alex O'Connell
|
de1cbcee83
|
add release notes
|
2024-04-24 21:23:28 -04:00 |
|
Alex O'Connell
|
92058d0694
|
manually set model language, zephyr2 prompt format , upgrading llama-cpp-python
|
2024-04-24 21:00:54 -04:00 |
|