Downloads · 30 days
11
8% of all-time downloads
replica-IEPile-Llama3.1-70B
necva/replica-IEPile-Llama3.1-70B
replica-IEPile-Llama3.1-70B is a machine learning model from necva. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
The model is instruction-tuned on IEpile dataset. The intended use of the model is Information Extraction tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Event Extraction (EE) The model is finetun…
All-time downloads
140
Public
Parameters
72.7B
39.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors39.5 GB · 100%
Parameter types
How the weights are stored.
U870.6B · 97%
Base models
Datasets
Model card
From the Hugging Face model README
The model is instruction-tuned on IEpile dataset. The intended use of the model is Information Extraction tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Event Extraction (EE) The model is finetuned based on IePile approach.
IEPile dataset
In IEPile, the instruction format of IEPile adopts a JSON-like string structure, which is essentially a dictionary-type string composed of the following three main components: (1) 'instruction': Task description, which outlines the task to be performed by the instruction (one of NER, RE, EE, EET, EEA). (2) 'schema': A list of schemas to be extracted (entity types, relation types, event types). (3) 'input': The text from which information is to be extracted.
- Type
- llama
- License
- mit
- Languages
- en
- Created
- Mar 7, 2025
- Updated
- Mar 10, 2025