Instructions to use handshake-ai-research/cue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use handshake-ai-research/cue with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="handshake-ai-research/cue", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("handshake-ai-research/cue", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from handshake-ai-research/cue: direct link, hf CLI and curl.
- Browser
- Download file 1.17 kB
-
https://huggingface.co/handshake-ai-research/cue/resolve/main/config.json
- Command line
-
hf download hf://handshake-ai-research/cue/config.json
-
curl -L -o config.json https://huggingface.co/handshake-ai-research/cue/resolve/main/config.json
1.17 kB
| { | |
| "architectures": [ | |
| "CueModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_cue.CueConfig", | |
| "AutoModel": "modeling_cue.CueModel" | |
| }, | |
| "command_slot_decode": true, | |
| "decoder": { | |
| "bottleneck_dim": 1024, | |
| "dtype": "bfloat16", | |
| "freeze_lm": false, | |
| "general_command_slots": 5, | |
| "injection": "flamingo_gated_xattn_dense", | |
| "insert_every": 4, | |
| "model_name": "Qwen/Qwen3-0.6B-Base", | |
| "num_heads": 8, | |
| "num_persona_tokens": 16, | |
| "slot_embedding_dim": 64, | |
| "style_command_slots": 5, | |
| "user_specific_command_slots": 5 | |
| }, | |
| "dual_decode": true, | |
| "encoder": { | |
| "bottleneck_dim": 1024, | |
| "max_length": 256, | |
| "max_turns": 64, | |
| "passage_prefix": "search_document: ", | |
| "query_prefix": "search_query: ", | |
| "session_dim": 1024, | |
| "session_heads": 8, | |
| "session_layers": 4, | |
| "system_model_name": "nomic-ai/modernbert-embed-base", | |
| "user_model_name": "nomic-ai/modernbert-embed-base" | |
| }, | |
| "example_pool_id": "handshake-ai-research/cue-example-pool", | |
| "general_command_slots": 5, | |
| "model_type": "cue", | |
| "slot_embedding_dim": 64, | |
| "style_command_slots": 5, | |
| "user_specific_command_slots": 5 | |
| } | |