jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
896 commits 1 branch 0 tags 1.4 MiB
Commit graph

7 commits

Author SHA1 Message Date
kingbri
ccf23243c1 Docs: Update getting started with downloading from private repos 
Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-03-19 12:02:48 -04:00
kingbri
79f9c6e854 Model: Remove num_experts_per_token 
This shouldn't even be an exposed option since changing it always
breaks inference with the model. Let the model's config.json handle
it.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-03-19 11:52:10 -04:00
kingbri
698d8339cb Config + Docs: Clarify YaRN rope scaling changes 
In ExllamaV2, if a model has YaRN support, linear RoPE options are
not applied. Users can set max_seq_len and exl2 will take care of
the rest.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-03-19 11:47:49 -04:00
kingbri
de77955428 Docs: Update 
Update getting started and server options

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-03-12 00:41:17 -04:00
kingbri
73688670a6 Docs: Add model and inline loading documentation 
Sorely required due to the amount of questions about how does inline
loading work.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-02-25 00:09:18 -05:00
kingbri
d6b8c7db4b Docs: Update getting started guide 
Add downloader options and edit some points.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-02-18 12:17:14 -05:00
kingbri
5614b342a7 Tree: Migrate docs into repository 
This will auto-publish to the Github wiki via an action.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
 2025-02-17 23:39:35 -05:00