ollama

Commit Graph

Author	SHA1	Message	Date
Ackermann Yuriy	154f24af91	Added missing options params to the embeddings docs (#472 )	3 years ago
Bruce MacDonald	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	3 years ago
Quinn Slack	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.	3 years ago
Jeffrey Morgan	d3b838ce60	update `orca` to `orca-mini`	3 years ago
Michael Yang	041f9ad1a1	update README.md	3 years ago
Bruce MacDonald	53bc36d207	Update modelfile.md	3 years ago
Bruce MacDonald	af98a1773f	update python example	3 years ago
Bruce MacDonald	9ae9a89883	Update modelfile.md	3 years ago
Bruce MacDonald	648f0974c6	python example	3 years ago
Bruce MacDonald	fc5230dffa	Add context to api docs	3 years ago
Güvenç Usanmaz	4c33a9ac67	Update langchainpy.md base_url value for Ollama object creation is corrected.	3 years ago
Matt Williams	202c29c21a	resolving bmacd comment Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	c1c871620a	Update docs/tutorials/langchainjs.md Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>	3 years ago
Matt Williams	a21a8bef56	Update docs/tutorials/langchainjs.md Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>	3 years ago
Matt Williams	522726228a	Update docs/tutorials.md Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>	3 years ago
Matt Williams	d3ee1329e9	Add tutorials for using Langchain with ollama Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Arturas Smorgun	d9c2687fd0	document default num_gqa to 1, as it's applicable to most models Co-authored-by: Michael Yang <mxyng@pm.me>	3 years ago
Arturas Smorgun	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	3 years ago
Jeffrey Morgan	be889b2f81	add docs for `/api/embeddings`	3 years ago
Jeffrey Morgan	7e26a8df31	cmd: use environment variables for server options	3 years ago
Michael Yang	37c9a8eea9	add lora docs	3 years ago
Bruce MacDonald	43c40c500e	add embed docs for modelfile	3 years ago
Bruce MacDonald	c4861360ec	remove embed docs	3 years ago
Jeffrey Morgan	371d4e5df3	docs: fix invalid json in `api.md`	3 years ago
Jeffrey Morgan	1f78e409b4	docs: format with `prettier`	3 years ago
Jeffrey Morgan	34a88cd776	docs: update `api.md` formatting	3 years ago
Bruce MacDonald	1bee2347be	pr feedback - defer closing llm on embedding - do not override licenses - remove debugging print line - reformat model file docs	3 years ago
Bruce MacDonald	3ceac05108	Add embedding docs	3 years ago
Matt Williams	1267895e44	missed a backtick Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	0c52b4509b	get rid of namespace and site Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	13aace3d34	clarify some more Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	2b3bb41598	model name format added Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	4904cd8bcd	update simpler code samples Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	8a45359ec6	Update docs/api.md Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	3 years ago
Matt Williams	2544b8afa1	update as per Mike's comments Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	ac1b04f271	Update docs/api.md Co-authored-by: Michael Yang <mxyng@pm.me>	3 years ago
Matt Williams	123fdeb919	Update docs/api.md Co-authored-by: Michael Yang <mxyng@pm.me>	3 years ago
Matt Williams	5c82bf95d1	Update docs/api.md Co-authored-by: Michael Yang <mxyng@pm.me>	3 years ago
Matt Williams	38a9b1618c	missed some quotes Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	c18be72a3b	complete 1st draft of api docs Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	a101fe51a7	clean up Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	d93e2f9210	fleshing out response Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	31edc829fc	continuing Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	b31104768c	filling out generate Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Matt Williams	b662d9fd8c	starting to build out some docs Signed-off-by: Matt Williams <m@technovangelist.com>	3 years ago
Michael Yang	da2459d519	Update README.md (#265 )	3 years ago
Bruce MacDonald	47bda0b860	add stop to docs	3 years ago
Bruce MacDonald	fee7687cf3	Update modelfile.md	3 years ago
Bruce MacDonald	1ac38ec89c	improve modelfile docs	3 years ago
Michael Yang	24e43e3212	update development.md	3 years ago

1 2

83 Commits (45ac07cd025f9d1e84917db3f00e0f3e5651aede)