Customise a model from the portal: a file, a model, a button
A page for anyone in a project, built for the one who knows least: an Excel, CSV or JSONL file of questions and answers, previewed; a model; a name; who may use it; and a button. The weights to train on are found from where the model's came (a GGUF repository's base model), the card's memory from their size, the node as the one with the most free. When it is done the adapter is published by itself (a llama.cpp model's replicas replaced to load it) and is a model of its own in the chat and the API. The project's by default; its members share it wider (confirmed, and never wider than the knowledge bases its pairs came from) or delete it. One trains at a time per project. ctl train start needs only --model and --data now, and --publish publishes when done. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
fcda4d3f85
commit
a53b2f4be9
33 files changed
+2199
-134
No files matched your search
@@ -0,0 +1,5 @@
|
||||
-- Training from the portal: the project a job was started in, which sees
|
||||
-- it, manages it and pays for it; and whether what it makes is published
|
||||
-- by itself when it is done, rather than by an administrator.
|
||||
ALTER TABLE train_jobs ADD COLUMN project_id TEXT NOT NULL DEFAULT '';
|
||||
ALTER TABLE train_jobs ADD COLUMN publish INTEGER NOT NULL DEFAULT 0;
|
||||
Reference in new issue
Block a user