EmpathicRobotics/vla-1.7b-qwen3-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: EmpathicRobotics/vla-1.7b-qwen3-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-31 04:48:17 +08:00
commit 42b9c1e645
37 changed files with 7011 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tools/decode/vendor/cosmos_tokenizer/NOTICE.md vendored Normal file
View File

@@ -0,0 +1,9 @@
Vendored from NVIDIA's [Cosmos-Tokenizer](https://github.com/NVIDIA/Cosmos-Tokenizer),
Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES, licensed under Apache-2.0
(see individual file headers). Vendored here (2026-07-23) so
`tools/decode/decode_cosmos.py` doesn't require the internal cluster's
`prototype/` directory (not part of this repo) -- only inference code
(`video_lib.py` + its direct dependencies) is included, not training code.
Model checkpoints are downloaded separately from
[nvidia/Cosmos-Tokenizer-DV8x16x16](https://huggingface.co/nvidia/Cosmos-Tokenizer-DV8x16x16)
on first use, not vendored here.