Commit graph

433 commits

Author SHA1 Message Date
Daniel Hiltgen 35934b2e05 Adapted rocm support to cgo based llama.cpp 2023-12-19 09:05:46 -08:00
Daniel Hiltgen d4cd695759 Add cgo implementation for llama.cpp
Run the server.cpp directly inside the Go runtime via cgo
while retaining the LLM Go abstractions.
2023-12-19 09:05:46 -08:00
Bruce MacDonald 5e7fd6906f Update images.go 2023-12-19 09:05:46 -08:00
Bruce MacDonald 811b1f03c8 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>
2023-12-19 09:05:46 -08:00
Bruce MacDonald d99fa6ce0a
send empty messages on last chat response (#1530) 2023-12-18 14:23:38 -05:00
Patrick Devine 3948c6ea06
add magic header for unit tests (#1558) 2023-12-18 10:41:02 -08:00
Patrick Devine 86b0dd4b16
add API create/copy handlers (#1541) 2023-12-15 11:59:18 -08:00
Patrick Devine 0174665d0e
add API tests for list handler (#1535) 2023-12-14 18:18:25 -08:00
Patrick Devine 630518f0d9
Add unit test of API routes (#1528) 2023-12-14 16:47:40 -08:00
Bruce MacDonald 6ee8c80199
restore model load duration on generate response (#1524)
* restore model load duration on generate response

- set model load duration on generate and chat done response
- calculate createAt time when response created

* remove checkpoints predict opts

* Update routes.go
2023-12-14 12:15:50 -05:00
Jeffrey Morgan 4a1abfe4fa fix tests 2023-12-13 14:42:30 -05:00
Patrick Devine d9e60f634b
add image support to the chat api (#1490) 2023-12-12 13:28:58 -08:00
Jeffrey Morgan 0a9d348023
Fix issues with /set template and /set system (#1486) 2023-12-12 14:43:19 -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
Jeffrey Morgan 7db5bcf73b fix go-staticcheck warning 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 9e1406e4ed Don't expose model information in /api/generate 2023-12-09 02:05:43 -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
Michael Yang 1f05d77110
Merge pull request #1244 from jmorganca/brucemacd/no-fail-template
do not fail on unsupported template variables
2023-12-06 13:23:04 -08:00
Michael Yang c3ff36088b
Merge pull request #774 from jmorganca/mxyng/server-version
add version api and show server version in cli
2023-12-06 13:22:55 -08:00
Bruce MacDonald 47d4e22673 use missingkey in set empty interface when missing 2023-12-05 15:49:05 -08:00
Michael Yang 5d75505ebd return model configuration in generate 2023-12-05 14:39:02 -08:00
Michael Yang b9495ea162 load projectors 2023-12-05 14:36:12 -08:00
Michael Yang 409bb9674e
Merge pull request #1308 from jmorganca/mxyng/split-from
split from into one or more models
2023-12-05 14:33:03 -08:00
Michael Yang d3479c07a1
Merge pull request #1250 from jmorganca/mxyng/create-layer
refactor layer creation
2023-12-05 14:32:52 -08:00
Bruce MacDonald 195e3d9dbd
chat api endpoint (#1392) 2023-12-05 14:57:33 -05:00
Michael Yang 1ebdbd9694 server: add version handler 2023-12-05 09:36:01 -08:00
Jeffrey Morgan 00d06619a1 Revert "chat api (#991)" while context variable is fixed
This reverts commit 7a0899d62d.
2023-12-04 21:16:27 -08:00
Michael Yang a3737cbd33 use NewLayer for CreateBlobHandler 2023-12-04 16:59:23 -08:00
Michael Yang 998f1785b6 add modelfamilies 2023-12-04 16:59:23 -08:00
Michael Yang 70a93057cd refactor layer creation
previous layer creation was not ideal because:

1. it required reading the input file multiple times, once to calculate
   the sha256 checksum, another to write it to disk, and potentially one
   more to decode the underlying gguf
2. used io.ReadSeeker which is prone to user error. if the file isn't
   reset correctly or in the right place, it could end up reading an
   empty file

there are also some brittleness when reading existing layers else
writing the inherited layers will error reading an already closed file

this commit aims to fix these issues by restructuring layer creation.

1. it will now write the layer to a temporary file as well as the hash
   function and move it to the final location on Commit
2. layers are read once once when copied to the destination. exception
   is raw model files which still requires a second read to decode the
   model metadata
2023-12-04 16:59:23 -08:00
Michael Yang 2cb0fa7d40 split from into one or more models 2023-12-04 16:59:23 -08:00
Bruce MacDonald 7a0899d62d
chat api (#991)
- update chat docs
- add messages chat endpoint
- remove deprecated context and template generate parameters from docs
- context and template are still supported for the time being and will continue to work as expected
- add partial response to chat history
2023-12-04 18:01:06 -05:00
Joshua Pham bb80a597db Fix adapter loading from SHA hash 2023-12-01 13:50:55 -05:00
Michael Yang 13efd5f218 upload: fix PUT retry 2023-11-29 16:38:35 -08:00
Michael Yang c4bdfffd96 upload: separate progress tracking 2023-11-29 16:38:33 -08:00
Michael Yang 26c63418e0 new hasher 2023-11-29 14:52:41 -08:00
Michael Yang 2799784ac8 revert checksum calculation to calculate-as-you-go 2023-11-29 13:47:58 -08:00
Bruce MacDonald 96122b7271
validate model tags on copy (#1323) 2023-11-29 15:54:29 -05:00
Timothy Jaeryang Baek c2e3b89176
fix: disable ':' in tag names (#1280)
Co-authored-by: rootedbox
2023-11-29 13:33:45 -05:00
Patrick Devine cde31cb220
Allow setting parameters in the REPL (#1294) 2023-11-29 09:56:42 -08:00
Bruce MacDonald 37d95157df
fix relative path on create (#1222) 2023-11-21 15:43:17 -05:00
Jeffrey Morgan 35c4b5ec16 calculate hash separately from http request 2023-11-20 15:45:11 -05:00
Jeffrey Morgan 9d73d3a6b5 add back part.Reset() 2023-11-19 14:32:19 -05:00
Jeffrey Morgan 72cd336410 dont retry on upload complete context cancel 2023-11-19 14:32:19 -05:00
Jeffrey Morgan 1bd594b2fa revert to using one open file for blob uploads 2023-11-19 14:32:19 -05:00
Jeffrey Morgan 9a8c21ac3d use exponential everywhere 2023-11-19 14:32:19 -05:00
Jeffrey Morgan f6b317e8c9 fix sending too little data in chunk upload body 2023-11-19 14:32:19 -05:00
Jeffrey Morgan ac5076ce1e exponential backoff up to 30s 2023-11-19 14:32:19 -05:00
Michael Yang 42c2e3a624 upload: retry complete upload 2023-11-19 14:32:19 -05:00
Michael Yang cb42589792 adjust download/upload parts 2023-11-19 14:32:19 -05:00
Jeffrey Morgan e1d7056496 update progress statuses 2023-11-19 09:21:13 -05:00
Jeffrey Morgan 02524a56ff check retry for authorization error 2023-11-19 00:19:53 -05:00
Jeffrey Morgan 12e046f12a remove unused function 2023-11-18 22:16:51 -05:00
Bruce MacDonald 43a726149d fix potentially inaccurate error message 2023-11-18 21:25:07 -05:00
Jeffrey Morgan bab9494176 add - separator to temp file created on ollama create 2023-11-18 09:39:52 -05:00
Michael Yang c6e6c8ee7e fix cross device rename 2023-11-17 15:22:17 -08:00
Michael Yang c1bbf5ddee
Merge pull request #1134 from jmorganca/mxyng/progress
progress bar
2023-11-17 14:03:35 -08:00
Bruce MacDonald 0b19e24d81
only retry once on auth failure (#1175) 2023-11-17 14:22:35 -05:00
Michael Yang d6ecaa2cbf update progress responses 2023-11-17 10:06:19 -08:00
Bruce MacDonald 4b3f4bc7d9
return failure details when unauthorized to push (#1131)
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-16 16:44:18 -05:00
Michael Yang a5ccf742c1 fix cross repo mounts 2023-11-16 16:33:30 -05:00
Michael Yang e33ef391cd fix push scope error for inherited model 2023-11-16 16:33:30 -05:00
Michael Yang 54f92f01cb update docs 2023-11-15 15:28:15 -08:00
Michael Yang 652d90e1c7 Update server/images.go
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-15 15:16:23 -08:00
Michael Yang bc22d5a38b no blob response 2023-11-15 15:16:23 -08:00
Michael Yang 1901044b07 use checksum reference 2023-11-15 15:16:23 -08:00
Michael Yang a07c935d34 ignore non blobs 2023-11-15 15:16:23 -08:00
Michael Yang 1552cee59f client create modelfile 2023-11-15 15:16:23 -08:00
Michael Yang 3ca56b5ada add create modelfile field 2023-11-15 15:16:23 -08:00
Michael Yang b0d14ed51c refactor create model 2023-11-15 15:16:23 -08:00
Michael Yang d91c103e74
Merge pull request #1055 from dansreis/946-fix-incorrect-base-model-name
Fixed incorrect base model name
2023-11-13 08:42:55 -08:00
Daniel Reis 7c438f2c53 Replaced method 2023-11-10 20:22:03 +00:00
Daniel Reis 6e46338d44 Reverting previous changes 2023-11-10 20:21:35 +00:00
Daniel Hiltgen cc54a416c6 Resume chunk download on UnexpectedEOF errors
If the chunk download is interrupted, resume from where we left off
2023-11-10 08:29:42 -08:00
Jeffrey Morgan 5cba29b9d6
JSON mode: add `"format" as an api parameter (#1051)
* add `"format": "json"` as an API parameter
---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-09 16:44:02 -08:00
Daniel Reis d17730356a Removed inline parse model path 2023-11-09 22:44:26 +00:00
Daniel Reis 32d79a6eea Using 'GetShortTagname' method instead 2023-11-09 22:40:37 +00:00
Bruce MacDonald ec2a31e9b3
support raw generation requests (#952)
- add the optional `raw` generate request parameter to bypass prompt formatting and response context
-add raw request to docs
2023-11-08 14:05:02 -08:00
Michael Yang 146072113d
Merge pull request #993 from jmorganca/mxyng/cleanup
cleanup upload and download errors
2023-11-06 11:32:12 -08:00
Jeffrey Morgan e21579a0f1 Restore system prompt on requests 2023-11-03 17:26:45 -07:00
Michael Yang 434a6f9d46 return last error 2023-11-03 16:49:51 -07:00
Michael Yang 84725ec7e3 refactor part reset 2023-11-03 09:20:32 -07:00
Noah Gitsham 8ae8c9fa8c
Remove duplicate "install" in GPU support warning (#984) 2023-11-03 00:45:14 -07:00
Noah Gitsham f39daff461
Add missing "be" to GPU support warning message (#983) 2023-11-02 18:37:12 -07:00
Jeffrey Morgan c50b01bc21 check request.Context for initial system prompt 2023-11-02 18:17:00 -07:00
Bruce MacDonald b9dc875401
remove modelfile context deprecated in v0.0.7 (#974) 2023-11-02 20:52:56 -04:00
Michael Yang 1fd511e661
Merge pull request #975 from jmorganca/mxyng/downloads
update downloads to use retry wrapper
2023-11-02 16:12:48 -07:00
Jeffrey Morgan 1beb5645a9
only use system prompt if context is not provided (#978) 2023-11-02 15:48:02 -07:00
Michael Yang fe5a872444 fix upload 2023-11-02 13:25:58 -07:00
Michael Yang d39709260f download with retry 2023-11-02 13:16:11 -07:00
Michael Yang 60bb3c03a1 use http.Method 2023-11-02 13:12:45 -07:00
Michael Yang c4cc738cbf fix log 2023-11-01 17:18:11 -07:00
Michael Yang 2c6189f4fe
Merge pull request #750 from jmorganca/mxyng/concurrent-uploads
concurrent uploads
2023-11-01 15:00:01 -07:00
Bruce MacDonald f9a4281124
clean up: remove server functions from client (#937) 2023-10-30 11:10:18 -04:00
Michael Yang 115fc56eb7 calculate and verify md5 checksum 2023-10-27 17:07:33 -07:00