ollama

baalajimaestro/ollama

Fork 0

Commit graph

f8ef4439e9 Use build tags to generate accelerated binaries for CUDA and ROCm on Linux. 65a 2023-10-16 17:41:40 -07:00
d4cd695759 Add cgo implementation for llama.cpp Daniel Hiltgen 2023-11-13 17:20:34 -08:00
5e7fd6906f Update images.go Bruce MacDonald 2023-12-11 15:35:31 -05:00
811b1f03c8 deprecate ggml Bruce MacDonald 2023-11-24 13:58:09 -05:00
ed195f3562

Merge pull request #1595 from pgibler/main Matt Williams 2023-12-18 20:55:18 -08:00
e0d0072ef1

Merge pull request #1592 from jmorganca/mattw/examplepruning Matt Williams 2023-12-18 20:29:48 -08:00
620a2ffcfb Added cmdh to community section in README pgibler 2023-12-18 22:04:40 -05:00
d287013f24 Lets get rid of these old modelfile examples Matt Williams 2023-12-18 17:47:33 -08:00
6b5bdfa6c9 update runner submodule Jeffrey Morgan 2023-12-18 17:33:46 -05:00
c063ee4af0 update runner submodule to fix hipblas build Jeffrey Morgan 2023-12-18 15:41:13 -05:00
d99fa6ce0a

send empty messages on last chat response (#1530) Bruce MacDonald 2023-12-18 14:23:38 -05:00
3948c6ea06

add magic header for unit tests (#1558) Patrick Devine 2023-12-18 10:41:02 -08:00
b85982eb91 update runner submodule Jeffrey Morgan 2023-12-18 12:43:31 -05:00
86b0dd4b16

add API create/copy handlers (#1541) Patrick Devine 2023-12-15 11:59:18 -08:00
f728738427

README with Enchanted iOS App (#1529) Augustinas Malinauskas 2023-12-15 19:37:29 +00:00
115048a0d8

Added Bionic GPT as a front end. (#1463) Ian Purton 2023-12-15 20:33:04 +01:00
1b417a7836

use exp slices for go 1.20 compatibility (#1544) Bruce MacDonald 2023-12-15 14:15:56 -05:00
0174665d0e

add API tests for list handler (#1535) Patrick Devine 2023-12-14 18:18:25 -08:00
630518f0d9

Add unit test of API routes (#1528) Patrick Devine 2023-12-14 16:47:40 -08:00
6e16098a60

remove sample_count from docs (#1527) Bruce MacDonald 2023-12-14 17:49:00 -05:00
6ee8c80199

restore model load duration on generate response (#1524) Bruce MacDonald 2023-12-14 12:15:50 -05:00
31f0551dab

Update runner to support mixtral and mixture of experts (MoE) (#1475) Jeffrey Morgan 2023-12-13 17:15:10 -05:00
4a1abfe4fa fix tests Jeffrey Morgan 2023-12-13 14:42:30 -05:00
bbd41494bf add multimodal to README.md Jeffrey Morgan 2023-12-13 14:38:47 -05:00
fedba24a63

Docs for multimodal support (#1485) Jeffrey Morgan 2023-12-13 13:59:33 -05:00
e3b090dbc5

Added message format for chat api (#1488) pepperoni21 2023-12-13 17:21:23 +01:00
d9e60f634b

add image support to the chat api (#1490) Patrick Devine 2023-12-12 13:28:58 -08:00
4251b342de

Merge pull request #1469 from jmorganca/mxyng/model-types Michael Yang 2023-12-12 12:27:03 -08:00
0a9d348023

Fix issues with /set template and /set system (#1486) Jeffrey Morgan 2023-12-12 14:43:19 -05:00
3144e2a439

exponential back-off (#1484) Bruce MacDonald 2023-12-12 12:33:02 -05:00
c0960e29b5

retry on concurrent request failure (#1483) Bruce MacDonald 2023-12-12 12:14:35 -05:00
5314fc9b63

Fix Readme "Database -> MindsDB" link (#1479) ruecat 2023-12-12 18:26:13 +03:00
a36b5fef3b

Update README.md (#1412) Jorge Torres 2023-12-11 15:05:10 -08:00
910e9401d0

Multimodal support (#1216) Patrick Devine 2023-12-11 13:56:22 -08:00
56ffc3023a remove per-model types Michael Yang 2023-12-08 16:39:26 -08:00
7a1b37ac64

os specific ctrl-z (#1420) Bruce MacDonald 2023-12-11 10:48:14 -05:00
5d4d2e2c60 update docs with chat completion api Jeffrey Morgan 2023-12-10 13:53:36 -05:00
7db5bcf73b fix go-staticcheck warning Jeffrey Morgan 2023-12-10 11:44:27 -05:00
fa2f095bd9 fix model name returned by /api/generate being different than the model name provided Jeffrey Morgan 2023-12-10 11:42:15 -05:00
045b855db9 fix error on accumulating final chat response Jeffrey Morgan 2023-12-10 11:24:39 -05:00
32064a0646 fix empty response when receiving runner error Jeffrey Morgan 2023-12-10 10:53:38 -05:00
d9a250e9b5 seek to end of file when decoding older model formats Jeffrey Morgan 2023-12-09 21:14:35 -05:00
944519ed16 seek to eof for older model binaries Jeffrey Morgan 2023-12-09 20:48:57 -05:00
2dd040d04c do not use --parallel 2 for old runners Jeffrey Morgan 2023-12-09 20:17:33 -05:00
bbe41ce41a

fix: parallel queueing race condition caused silent failure (#1445) Bruce MacDonald 2023-12-09 14:14:02 -05:00
9e1406e4ed Don't expose model information in /api/generate Jeffrey Morgan 2023-12-09 02:05:43 -08:00
b74580c913

Update api.md Jeffrey Morgan 2023-12-08 16:02:07 -08:00
7e9405fd07

fix: encode full previous prompt in context (#1424) Bruce MacDonald 2023-12-08 16:53:51 -05:00
3b0b8930d4

fix: only flush template in chat when current role encountered (#1426) Bruce MacDonald 2023-12-08 16:44:24 -05:00
e3f925fc1b

fix: restore modelfile system in prompt template (#1425) Bruce MacDonald 2023-12-08 14:20:19 -05:00
2a2289fb6b

Update api.md Jeffrey Morgan 2023-12-08 09:36:45 -08:00
dd427f499a

Merge pull request #1419 from jmorganca/mattw/typescript-simplechat Matt Williams 2023-12-07 14:42:24 -08:00
2ae573c7ed

Merge pull request #1421 from jmorganca/mxyng/fix-newline Michael Yang 2023-12-07 13:47:23 -08:00
02fe26c44b update the readme as per bruce Matt Williams 2023-12-07 13:46:30 -08:00
16c7548460 fix redundant newline Michael Yang 2023-12-07 13:44:45 -08:00
fa75998c0d

Update examples/typescript-simplechat/readme.md Matt Williams 2023-12-07 13:40:54 -08:00
5344f886c8

Update examples/typescript-simplechat/client.ts Matt Williams 2023-12-07 13:40:37 -08:00
6cc823c9b5

Update examples/typescript-simplechat/client.ts Matt Williams 2023-12-07 13:39:59 -08:00
b84d34e632

Update examples/typescript-simplechat/readme.md Matt Williams 2023-12-07 13:39:33 -08:00
30229a913c

Update examples/typescript-simplechat/client.ts Matt Williams 2023-12-07 13:39:24 -08:00
1ade380bd7 Simple chat example for typescript Matt Williams 2023-12-07 11:48:25 -08:00
ba264e9da8 add future version note to chat api docs Jeffrey Morgan 2023-12-07 09:41:56 -08:00
a2405ec831

Merge pull request #1409 from jmorganca/mattw/python-simplechat Matt Williams 2023-12-06 15:49:45 -08:00
ce809bb529 Merge branch 'mattw/python-simplechat' of github.com:jmorganca/ollama into mattw/python-simplechat Matt Williams 2023-12-06 15:48:42 -08:00
76bc4d0458 Cleanup as per Bruce Matt Williams 2023-12-06 15:44:40 -08:00
4a02945a15

Update examples/python-simplechat/client.py Bruce MacDonald 2023-12-06 18:36:45 -05:00
aec742b6d2

Update examples/python-simplechat/readme.md Matt Williams 2023-12-06 15:30:45 -08:00
f337642e94

Update examples/python-simplechat/readme.md Matt Williams 2023-12-06 15:30:35 -08:00
51131cc6e2

Update examples/python-simplechat/client.py Matt Williams 2023-12-06 15:30:10 -08:00
43027789dc Simple chat example Matt Williams 2023-12-06 14:35:58 -08:00
f9b7d65e2b

docs/tutorials: add bit on how to use Fly GPUs on-demand with Ollama (#1406) Xe Iaso 2023-12-06 17:14:02 -05:00
1f05d77110

Merge pull request #1244 from jmorganca/brucemacd/no-fail-template Michael Yang 2023-12-06 13:23:04 -08:00
c3ff36088b

Merge pull request #774 from jmorganca/mxyng/server-version Michael Yang 2023-12-06 13:22:55 -08:00
13524b5e72

List "Send chat messages" in table of contents (#1399) Samuel Calderon 2023-12-06 15:34:27 -05:00
f1b049fed8

Merge pull request #1377 from jmorganca/mxyng/qwen Michael Yang 2023-12-06 12:31:51 -08:00
97c5696945 fix base urls in chat examples Jeffrey Morgan 2023-12-06 12:10:20 -08:00
47d4e22673 use missingkey in set empty interface when missing Bruce MacDonald 2023-11-22 14:46:49 -05:00
32f62fbb8e

Merge pull request #1334 from jmorganca/mxyng/load-projectors Michael Yang 2023-12-05 14:40:53 -08:00
5d75505ebd return model configuration in generate Michael Yang 2023-12-01 11:37:17 -08:00
b9495ea162 load projectors Michael Yang 2023-11-30 10:30:23 -08:00
409bb9674e

Merge pull request #1308 from jmorganca/mxyng/split-from Michael Yang 2023-12-05 14:33:03 -08:00
d3479c07a1

Merge pull request #1250 from jmorganca/mxyng/create-layer Michael Yang 2023-12-05 14:32:52 -08:00
b12f1b984f

Merge pull request #1393 from jmorganca/mxyng/fix-whitespace Michael Yang 2023-12-05 12:18:01 -08:00
195e3d9dbd

chat api endpoint (#1392) Bruce MacDonald 2023-12-05 14:57:33 -05:00
38fe1a368b fix: trim space in modelfile fields Michael Yang 2023-12-05 11:57:21 -08:00
4b77fcb2b9 comments Michael Yang 2023-12-01 12:10:27 -08:00
cde13bcdea cmd: only print server version when different Michael Yang 2023-10-16 09:57:19 -07:00
0f0cd265a7 cmd: add server version Michael Yang 2023-11-22 09:41:02 -08:00
0db4706ec2 api: add version api handler Michael Yang 2023-11-22 09:41:44 -08:00
1ebdbd9694 server: add version handler Michael Yang 2023-10-12 15:45:07 -07:00
5c59455b59 cmd: use existing cmd context Michael Yang 2023-10-12 15:56:40 -07:00
00d06619a1 Revert "chat api (#991)" while context variable is fixed Jeffrey Morgan 2023-12-04 21:16:27 -08:00
f1ef3f9947

remove mention of gpt-neox in import (#1381) Matt Williams 2023-12-04 20:58:10 -08:00
5a5dca13b2 comments Michael Yang 2023-11-29 10:54:23 -08:00
72e7a49aa9 seek instead of copyn Michael Yang 2023-11-29 10:31:58 -08:00
998f1785b6 add modelfamilies Michael Yang 2023-11-29 11:11:42 -08:00
2cb0fa7d40 split from into one or more models Michael Yang 2023-11-24 11:57:20 -08:00
7232f1fa41 go mod tidy Michael Yang 2023-11-22 15:52:23 -08:00
a3737cbd33 use NewLayer for CreateBlobHandler Michael Yang 2023-11-24 12:01:23 -08:00
70a93057cd refactor layer creation Michael Yang 2023-11-22 13:28:49 -08:00