michaelborck / refuled

Refuel LLM 2 is a specialised language model designed for data labelling, data enrichment, and data cleaning tasks. It automates the labor-intensive process of data management, and data labelling.

8B

44 Pulls Updated 5 months ago

5 months ago

9769cb024ffe · 4.9GB

model
llama
·
8.03B
·
Q4_K_M
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>

Readme

Model Overview

Refuel LLM 2 is a specialised language model designed for data labelling, data enrichment, and data cleaning tasks. It automates the labor-intensive process of data management, and data labelling.

Performance and Comparison

This model has outperformed other state-of-the-art models like GP4 Turbo, CLAE 3, Opus, and Gemini 1.5 Pro across a range of data labelling tasks. See Hugging Face model card for detailed performance benchmarks.

Technical Specifications

Built on LAMA 38 billion instruct, an auto regressive language model with an optimised Transformer architecture, Refuel LLM 2 is fine-tuned on a diverse corpus of 2,750+ datasets for various tasks like classification and entity resolution.

Model Details (from Hugging Face card)

RefuelLLM-2-small, aka Llama-3-Refueled, is a Llama3-8B base model instruction tuned on a corpus of 2750+ datasets, spanning tasks such as classification, reading comprehension, structured attribute extraction and entity resolution. We’re excited to open-source the model for the community to build on top of.