third-party-mirrors/ollama
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,602 Commits 177 Branches 161 Tags
Commit Graph

1602 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Daniel Hiltgen
aa10cae558 Adapted rocm support to cgo based llama.cpp 2023-12-12 17:26:43 -08:00
65a
f3bdb2efd9 Use build tags to generate accelerated binaries for CUDA and ROCm on Linux. 
The build tags rocm or cuda must be specified to both go generate and go build.
ROCm builds should have both ROCM_PATH set (and the ROCM SDK present) as well
as CLBlast installed (for GGML) and CLBlast_DIR set in the environment to the
CLBlast cmake directory (likely /usr/lib/cmake/CLBlast). Build tags are also
used to switch VRAM detection between cuda and rocm implementations, using
added "accelerator_foo.go" files which contain architecture specific functions
and variables. accelerator_none is used when no tags are set, and a helper
function addRunner will ignore it if it is the chosen accelerator. Fix go
generate commands, thanks @deadmeu for testing.
 2023-12-12 17:26:43 -08:00
Daniel Hiltgen
051a3d271c Add cgo implementation for llama.cpp 
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
 2023-12-12 17:26:43 -08:00
Bruce MacDonald
4b20d49539 Update images.go 2023-12-12 15:45:00 -08:00
Bruce MacDonald
f8487f433f deprecate ggml 
- remove ggml runner
- automatically pull gguf models when ggml detected
- tell users to update to gguf in the case automatic pull fails

Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
 2023-12-12 15:45:00 -08:00
Patrick Devine
d9e60f634b
add image support to the chat api (#1490) v0.1.15 2023-12-12 13:28:58 -08:00
Michael Yang
4251b342de
Merge pull request #1469 from jmorganca/mxyng/model-types 
remove per-model types
 2023-12-12 12:27:03 -08:00
Jeffrey Morgan
0a9d348023
Fix issues with /set template and /set system (#1486) 2023-12-12 14:43:19 -05:00
Bruce MacDonald
3144e2a439
exponential back-off (#1484) 2023-12-12 12:33:02 -05:00
Bruce MacDonald
c0960e29b5
retry on concurrent request failure (#1483) 
- remove parallel
 2023-12-12 12:14:35 -05:00
ruecat
5314fc9b63
Fix Readme "Database -> MindsDB" link (#1479) 2023-12-12 10:26:13 -05:00
Jorge Torres
a36b5fef3b
Update README.md (#1412) 2023-12-11 18:05:10 -05:00
Patrick Devine
910e9401d0
Multimodal support (#1216) 
---------

Co-authored-by: Matt Apperson <mattapperson@Matts-MacBook-Pro.local>
 2023-12-11 13:56:22 -08:00
Michael Yang
56ffc3023a remove per-model types 
mostly replaced by decoding tensors except ggml models which only
support llama
 2023-12-11 09:40:21 -08:00
Bruce MacDonald
7a1b37ac64
os specific ctrl-z (#1420) 2023-12-11 10:48:14 -05:00
Jeffrey Morgan
5d4d2e2c60 update docs with chat completion api 2023-12-10 13:53:36 -05:00
Jeffrey Morgan
7db5bcf73b fix go-staticcheck warning v0.1.14 2023-12-10 11:44:27 -05:00
Jeffrey Morgan
fa2f095bd9 fix model name returned by /api/generate being different than the model name provided 2023-12-10 11:42:15 -05:00
Jeffrey Morgan
045b855db9 fix error on accumulating final chat response 2023-12-10 11:24:39 -05:00
Jeffrey Morgan
32064a0646 fix empty response when receiving runner error 2023-12-10 10:53:38 -05:00
Jeffrey Morgan
d9a250e9b5 seek to end of file when decoding older model formats 2023-12-09 21:14:35 -05:00
Jeffrey Morgan
944519ed16 seek to eof for older model binaries 2023-12-09 20:48:57 -05:00
Jeffrey Morgan
2dd040d04c do not use --parallel 2 for old runners 2023-12-09 20:17:33 -05:00
Bruce MacDonald
bbe41ce41a
fix: parallel queueing race condition caused silent failure (#1445) 
* fix: queued request failures

- increase parallel requests to 2 to complete queued request, queueing is managed in ollama

* log steam errors
 2023-12-09 14:14:02 -05:00
Jeffrey Morgan
9e1406e4ed Don't expose model information in /api/generate 2023-12-09 02:05:43 -08:00
Jeffrey Morgan
b74580c913
Update api.md 2023-12-08 16:02:07 -08:00
Bruce MacDonald
7e9405fd07
fix: encode full previous prompt in context (#1424) 2023-12-08 16:53:51 -05:00
Bruce MacDonald
3b0b8930d4
fix: only flush template in chat when current role encountered (#1426) 2023-12-08 16:44:24 -05:00
Bruce MacDonald
e3f925fc1b
fix: restore modelfile system in prompt template (#1425) 2023-12-08 14:20:19 -05:00
Jeffrey Morgan
2a2289fb6b
Update api.md 2023-12-08 09:36:45 -08:00
Matt Williams
dd427f499a
Merge pull request #1419 from jmorganca/mattw/typescript-simplechat 
Simple chat example for typescript
 2023-12-07 14:42:24 -08:00
Michael Yang
2ae573c7ed
Merge pull request #1421 from jmorganca/mxyng/fix-newline 
fix redundant newline
 2023-12-07 13:47:23 -08:00
Matt Williams
02fe26c44b update the readme as per bruce 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-12-07 13:46:30 -08:00
Michael Yang
16c7548460 fix redundant newline 2023-12-07 13:44:45 -08:00
Matt Williams
fa75998c0d
Update examples/typescript-simplechat/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-07 13:40:54 -08:00
Matt Williams
5344f886c8
Update examples/typescript-simplechat/client.ts 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-07 13:40:37 -08:00
Matt Williams
6cc823c9b5
Update examples/typescript-simplechat/client.ts 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-07 13:39:59 -08:00
Matt Williams
b84d34e632
Update examples/typescript-simplechat/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-07 13:39:33 -08:00
Matt Williams
30229a913c
Update examples/typescript-simplechat/client.ts 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-07 13:39:24 -08:00
Matt Williams
1ade380bd7 Simple chat example for typescript 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-12-07 11:48:25 -08:00
Jeffrey Morgan
ba264e9da8 add future version note to chat api docs 2023-12-07 09:42:15 -08:00
Matt Williams
a2405ec831
Merge pull request #1409 from jmorganca/mattw/python-simplechat 
Simple chat example
 2023-12-06 15:49:45 -08:00
Matt Williams
ce809bb529 Merge branch 'mattw/python-simplechat' of github.com:jmorganca/ollama into mattw/python-simplechat 2023-12-06 15:48:42 -08:00
Matt Williams
76bc4d0458 Cleanup as per Bruce 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-12-06 15:44:40 -08:00
Bruce MacDonald
4a02945a15
Update examples/python-simplechat/client.py 2023-12-06 18:36:45 -05:00
Matt Williams
aec742b6d2
Update examples/python-simplechat/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-06 15:30:45 -08:00
Matt Williams
f337642e94
Update examples/python-simplechat/readme.md 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-06 15:30:35 -08:00
Matt Williams
51131cc6e2
Update examples/python-simplechat/client.py 
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
 2023-12-06 15:30:10 -08:00
Matt Williams
43027789dc Simple chat example 
Signed-off-by: Matt Williams <m@technovangelist.com>
 2023-12-06 14:35:58 -08:00
Xe Iaso
f9b7d65e2b
docs/tutorials: add bit on how to use Fly GPUs on-demand with Ollama (#1406) 
Signed-off-by: Xe Iaso <xe@camellia.finch-kitefin.ts.net>
 2023-12-06 14:14:02 -08:00