Instructions to use 10ths/FADS_base_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 10ths/FADS_base_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="10ths/FADS_base_model", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("10ths/FADS_base_model", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from 10ths/FADS_base_model: direct link, hf CLI and curl.
- Browser
- Download file 873 Bytes
-
https://huggingface.co/10ths/FADS_base_model/resolve/main/config.json
- Command line
-
hf download hf://10ths/FADS_base_model/config.json
-
curl -L -o config.json https://huggingface.co/10ths/FADS_base_model/resolve/main/config.json
873 Bytes
| { | |
| "_name_or_path": "Salesforce/xgen-mm-phi3-mini-instruct-r-v1", | |
| "architectures": [ | |
| "XGenMMModelForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "Salesforce/xgen-mm-phi3-mini-instruct-r-v1--configuration_xgenmm.XGenMMConfig", | |
| "AutoModelForVision2Seq": "Salesforce/xgen-mm-phi3-mini-instruct-r-v1--modeling_xgenmm.XGenMMModelForConditionalGeneration" | |
| }, | |
| "model_type": "xgenmm", | |
| "text_config": { | |
| "initial_tokenizer_len": 32012, | |
| "model_type": "phi3", | |
| "sliding_window": 2047, | |
| "torch_dtype": "bfloat16" | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.41.2", | |
| "vision_encoder_config": { | |
| "anyres_patch_sampling": true, | |
| "image_aspect_ratio": "anyres", | |
| "model_type": "xgenmm_vision_encoder" | |
| }, | |
| "vision_tokenizer_config": { | |
| "model_type": "xgenmm_vision_tokenizer" | |
| } | |
| } | |