Instructions to use LimitedMouse/Generative-Embedding-Benchmark-Checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LimitedMouse/Generative-Embedding-Benchmark-Checkpoints with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("LimitedMouse/Generative-Embedding-Benchmark-Checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download qwen3vl-2b/visual_only/decoder_config.json from LimitedMouse/Generative-Embedding-Benchmark-Checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 247 Bytes
-
https://huggingface.co/LimitedMouse/Generative-Embedding-Benchmark-Checkpoints/resolve/main/qwen3vl-2b/visual_only/decoder_config.json
- Command line
-
hf download hf://LimitedMouse/Generative-Embedding-Benchmark-Checkpoints/qwen3vl-2b/visual_only/decoder_config.json
-
curl -L -o decoder_config.json https://huggingface.co/LimitedMouse/Generative-Embedding-Benchmark-Checkpoints/resolve/main/qwen3vl-2b/visual_only/decoder_config.json
247 Bytes
| { | |
| "embed_dim": 2048, | |
| "base_model_name": "Qwen/Qwen3-0.6B", | |
| "adapter_hidden_dim": 1024, | |
| "hidden_dims": [ | |
| 1024 | |
| ], | |
| "lora_rank": 0, | |
| "lora_alpha": 32, | |
| "lora_target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "freeze_base": false | |
| } |