1255bc9b45
only package 11.8 runner
2023-09-20 20:00:41 +01:00
4e8be787c7
pack in cuda libs
2023-09-20 17:40:42 +01:00
2540c9181c
support for packaging in multiple cuda runners ( #509 )
...
* enable packaging multiple cuda versions
* use nvcc cuda version if available
---------
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-09-14 15:08:13 -04:00
fc8707686f
Update API docs ( #527 )
...
* Update API docs
Signed-off-by: Matt Williams <m@technovangelist.com >
* strange TOC was getting auto generated
Signed-off-by: Matt Williams <m@technovangelist.com >
* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
* Update docs/api.md
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
* Update api.md
---------
Signed-off-by: Matt Williams <m@technovangelist.com >
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
Co-authored-by: Michael Chiang <mchiang0610@users.noreply.github.com >
2023-09-14 08:51:26 -07:00
f221637053
first pass at linux gpu support ( #454 )
...
* linux gpu support
* handle multiple gpus
* add cuda docker image (#488 )
---------
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-09-12 11:04:35 -04:00
154f24af91
Added missing options params to the embeddings docs ( #472 )
2023-09-05 20:18:49 -04:00
42998d797d
subprocess llama.cpp server ( #401 )
...
* remove c code
* pack llama.cpp
* use request context for llama_cpp
* let llama_cpp decide the number of threads to use
* stop llama runner when app stops
* remove sample count and duration metrics
* use go generate to get libraries
* tmp dir for running llm
2023-08-30 16:35:03 -04:00
f4432e1dba
treat stop as stop sequences, not exact tokens ( #442 )
...
The `stop` option to the generate API is a list of sequences that should cause generation to stop. Although these are commonly called "stop tokens", they do not necessarily correspond to LLM tokens (per the LLM's tokenizer). For example, if the caller sends a generate request with `"stop":["\n"]`, then generation should stop on any token containing `\n` (and trim `\n` from the output), not just if the token exactly matches `\n`. If `stop` were interpreted strictly as LLM tokens, then it would require callers of the generate API to know the LLM's tokenizer and enumerate many tokens in the `stop` list.
Fixes https://github.com/jmorganca/ollama/issues/295 .
2023-08-30 11:53:42 -04:00
d3b838ce60
update orca to orca-mini
2023-08-27 13:26:30 -04:00
041f9ad1a1
update README.md
2023-08-25 11:44:25 -07:00
519f4d98ef
add embed docs for modelfile
2023-08-17 13:37:42 -04:00
23e1da778d
Add context to api docs
2023-08-15 11:43:22 -03:00
53bc36d207
Update modelfile.md
2023-08-15 09:23:36 -03:00
af98a1773f
update python example
2023-08-14 16:38:44 -03:00
9ae9a89883
Update modelfile.md
2023-08-14 16:26:53 -03:00
648f0974c6
python example
2023-08-14 15:27:13 -03:00
fc5230dffa
Add context to api docs
2023-08-14 15:23:24 -03:00
4c33a9ac67
Update langchainpy.md
...
base_url value for Ollama object creation is corrected.
2023-08-14 12:12:56 +03:00
202c29c21a
resolving bmacd comment
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-11 13:51:44 -07:00
c1c871620a
Update docs/tutorials/langchainjs.md
...
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
2023-08-11 13:48:46 -07:00
a21a8bef56
Update docs/tutorials/langchainjs.md
...
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
2023-08-11 13:48:35 -07:00
522726228a
Update docs/tutorials.md
...
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com >
2023-08-11 13:48:16 -07:00
d3ee1329e9
Add tutorials for using Langchain with ollama
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-10 21:27:37 -07:00
3a05d3def7
Merge pull request #326 from asarturas/document-num-gqa-parameter
...
Document num_gqa parameter
2023-08-10 18:18:38 -07:00
d9c2687fd0
document default num_gqa to 1, as it's applicable to most models
...
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-08-11 01:29:40 +01:00
6517bcc53c
Merge pull request #290 from jmorganca/add-adapter-layers
...
implement loading ggml lora adapters through the modelfile
2023-08-10 17:23:01 -07:00
c0e7a3b90e
Document num_gqa parameter
...
It is required to be adjusted for some models, see https://github.com/jmorganca/ollama/issues/320 for more context
2023-08-11 00:58:09 +01:00
be889b2f81
add docs for /api/embeddings
2023-08-10 15:56:59 -07:00
7e26a8df31
cmd: use environment variables for server options
2023-08-10 14:17:53 -07:00
37c9a8eea9
add lora docs
2023-08-10 09:23:40 -07:00
43c40c500e
add embed docs for modelfile
2023-08-09 16:14:58 -04:00
c4861360ec
remove embed docs
2023-08-09 16:14:19 -04:00
7a5f3616fd
embed text document in modelfile
2023-08-09 10:26:19 -04:00
371d4e5df3
docs: fix invalid json in api.md
2023-08-08 15:46:05 -07:00
1f78e409b4
docs: format with prettier
2023-08-08 15:41:48 -07:00
34a88cd776
docs: update api.md formatting
2023-08-08 15:41:19 -07:00
1bee2347be
pr feedback
...
- defer closing llm on embedding
- do not override licenses
- remove debugging print line
- reformat model file docs
2023-08-08 17:01:37 -04:00
3ceac05108
Add embedding docs
2023-08-08 14:04:11 -04:00
1267895e44
missed a backtick
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-07 13:53:49 -07:00
0c52b4509b
get rid of namespace and site
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-07 13:27:58 -07:00
13aace3d34
clarify some more
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-07 13:21:54 -07:00
2b3bb41598
model name format added
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-07 13:17:16 -07:00
4904cd8bcd
update simpler code samples
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-07 07:40:38 -07:00
8a45359ec6
Update docs/api.md
...
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com >
2023-08-07 07:33:05 -07:00
2544b8afa1
update as per Mike's comments
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-04 17:42:24 -07:00
ac1b04f271
Update docs/api.md
...
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-08-04 17:40:52 -07:00
123fdeb919
Update docs/api.md
...
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-08-04 17:38:52 -07:00
5c82bf95d1
Update docs/api.md
...
Co-authored-by: Michael Yang <mxyng@pm.me >
2023-08-04 17:12:24 -07:00
38a9b1618c
missed some quotes
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-04 16:09:07 -07:00
c18be72a3b
complete 1st draft of api docs
...
Signed-off-by: Matt Williams <m@technovangelist.com >
2023-08-04 16:08:11 -07:00
