21 Commits

Author	SHA1	Message	Date
James Murdza	ddc5a5de91	Format codebase with uv run pre-commit run --all-files	2025-10-22 11:35:31 -07:00
Dillon DuPont	1346feb125	Add postponed annotations to internvl.py	2025-09-19 19:23:13 -04:00
Dillon DuPont	6ddddf8f88	fix internVL inference	2025-09-16 12:56:07 -04:00
Dillon DuPont	9147e8eeaf	Added "cua-agent[internvl-hf]" dep	2025-09-16 12:02:07 -04:00
Dillon DuPont	c5bbd4611a	add qwen2_5_vl.py	2025-09-15 16:29:26 -04:00
Dillon DuPont	cf95646503	Merge branch 'main' into models/opencua	2025-09-12 13:30:21 -04:00
Dillon DuPont	e90997c4ff	Added screenshot_dir and lazy loading of MLX	2025-08-28 13:18:17 -04:00
Dillon DuPont	bf3c3256df	increased max tokens, added trust_remote_code kwarg	2025-08-26 18:15:24 -04:00
Dillon DuPont	eeb2be9b96	Fixed incorrect special token	2025-08-22 13:16:16 -04:00
Dillon DuPont	f72a03be97	Restored MLX/ adapter	2025-08-22 13:00:04 -04:00
Dillon DuPont	b20d2a0a93	Pinned transformers version, first working grounding version	2025-08-21 11:54:13 -04:00
Dillon DuPont	dad6634ffd	Added local inference routing for different models	2025-08-21 10:51:39 -04:00
Dillon DuPont	7e5ee5010b	added human adapter	2025-08-11 15:57:16 -04:00
Dillon DuPont	d8b1792cc5	Added human/ provider to liteLLM	2025-08-11 15:24:56 -04:00
Dillon DuPont	d172ca8563	fixed improper kwargs	2025-08-11 10:54:21 -04:00
Dillon DuPont	be1ce76849	Limited pytorch inference to 1 thread	2025-08-11 10:31:49 -04:00
Dillon DuPont	0063eccb79	Merge branch 'main' into feat/extra-models	2025-08-05 12:46:26 -04:00
cgutierr	9781810451	Move inputs to model's same device, previously hardcoded to CUDA	2025-08-03 13:02:15 +02:00
cgutierr	5b5f17af8e	Use generic AutoModel not tied to specific arch	2025-08-03 13:00:27 +02:00
Dillon DuPont	2076ec7596	added GTA1 agent and click benchmarks (ss-pro, repl)	2025-07-29 20:48:44 -04:00
Dillon DuPont	16d0abb332	Updated README, notebooks, docs	2025-07-28 10:17:04 -04:00