Feature Extraction
sentence-transformers
PyTorch
gpt_neo
sentence-similarity
mteb
Eval Results (legacy)
Instructions to use Muennighoff/SGPT-1.3B-weightedmean-msmarco-specb-bitfit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Muennighoff/SGPT-1.3B-weightedmean-msmarco-specb-bitfit with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Muennighoff/SGPT-1.3B-weightedmean-msmarco-specb-bitfit") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "EleutherAI/gpt-neo-1.3B", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPTNeoModel" | |
| ], | |
| "attention_dropout": 0, | |
| "attention_layers": [ | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local", | |
| "global", | |
| "local" | |
| ], | |
| "attention_types": [ | |
| [ | |
| [ | |
| "global", | |
| "local" | |
| ], | |
| 12 | |
| ] | |
| ], | |
| "bos_token_id": 50256, | |
| "embed_dropout": 0, | |
| "eos_token_id": 50256, | |
| "gradient_checkpointing": false, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neo", | |
| "num_heads": 16, | |
| "num_layers": 24, | |
| "resid_dropout": 0, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50, | |
| "temperature": 0.9 | |
| } | |
| }, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.20.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 50259, | |
| "window_size": 256 | |
| } | |