Featherless
ERank-4BAlibaba NLP
Start Chat
4B Params BF16 Open Weights Inference Available

Alibaba-NLP/ERank-4B is a 4 billion parameter pointwise reranker developed by Alibaba-NLP, designed for effective and efficient text reranking. It utilizes a novel two-stage training pipeline combining Supervised Fine-Tuning (SFT) for generative integer score output and Reinforcement Learning (RL) with a listwise derived reward. This model excels in diverse relevance scenarios, particularly reasoning-intensive tasks, while maintaining low latency compared to listwise rerankers. It supports customizable input instructions and offers a 40960 token context length.

Loading preview...

Parameters:4BContext length:32kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:August 2025
0.0M
0.0K

Model tree for

Alibaba-NLP/ERank-4B
Popular Sampler Settings

Most commonly used values from Featherless users

temperature

This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.

–

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

–

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

–

frequency_penalty

This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.

–

presence_penalty

This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.

–

repetition_penalty

This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.

–

min_p

This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.

–