Feature Extraction
Transformers
Safetensors
English
squeez-pooled
winnow
headroom
squeez
context-compression
coding-agents
tool-output
custom_code
Instructions to use rbk4209/winnow-pooled-32m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rbk4209/winnow-pooled-32m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="rbk4209/winnow-pooled-32m", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rbk4209/winnow-pooled-32m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from rbk4209/winnow-pooled-32m: direct link, hf CLI and curl.
- Browser
- Download file 2.62 kB
-
https://huggingface.co/rbk4209/winnow-pooled-32m/resolve/main/config.json
- Command line
-
hf download hf://rbk4209/winnow-pooled-32m/config.json
-
curl -L -o config.json https://huggingface.co/rbk4209/winnow-pooled-32m/resolve/main/config.json
2.62 kB
| { | |
| "architectures": [ | |
| "PooledLineClassifier" | |
| ], | |
| "base_model_name": "jhu-clsp/ettin-encoder-32m", | |
| "classifier_dropout": 0.1, | |
| "dtype": "float32", | |
| "encoder_config": { | |
| "_name_or_path": "jhu-clsp/ettin-encoder-32m", | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50281, | |
| "causal_mask": false, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50282, | |
| "global_attn_every_n_layers": 3, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 384, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 576, | |
| "is_causal": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "local_attention": 128, | |
| "max_position_embeddings": 7999, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 6, | |
| "num_hidden_layers": 10, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "sans_pos", | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 160000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 160000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": 50282, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.2.0", | |
| "vocab_size": 50368 | |
| }, | |
| "max_length": 4096, | |
| "model_type": "squeez-pooled", | |
| "transformers_version": "5.2.0", | |
| "use_cache": false, | |
| "vocab_size": 50369, | |
| "auto_map": { | |
| "AutoConfig": "modeling_squeez_pooled.PooledLineConfig", | |
| "AutoModel": "modeling_squeez_pooled.PooledLineClassifier" | |
| } | |
| } |