NeverSleep: Llama 3 Lumimaid 8B

Text input Text output Unavailable
Author's Description

The NeverSleep team is back, with a Llama 3 8B finetune trained on their curated roleplay data. Striking a balance between eRP and RP, Lumimaid was designed to be serious, yet uncensored when necessary. To enhance it's overall intelligence and chat capability, roughly 40% of the training data was not roleplay. This provides a breadth of knowledge to access, while still keeping roleplay as the primary strength. Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

Key Specifications
Cost
$$$
Context
24K
Parameters
8B
Released
May 03, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Stop Presence Penalty Logit Bias Top P Temperature Min P Seed Frequency Penalty Max Tokens
Performance Summary

NeverSleep: Llama 3 Lumimaid 8B demonstrates competitive response times, performing among the faster models with a 52nd percentile ranking in speed. It also offers cost-effective solutions, ranking in the 63rd percentile for price. The model's performance across various benchmarks indicates a clear specialization. While its accuracy in Classification (Email Classification: 93.0%) is a notable strength, aligning with its description of balancing general intelligence with roleplay, its performance in more analytical and knowledge-based tasks is consistently lower. For instance, it achieved 45.0% in Coding, 30.4% in Reasoning, 61.0% in Ethics, and 66.5% in General Knowledge, placing it in the lower percentiles for accuracy in these categories. This suggests that while Lumimaid excels at structured classification, its capabilities in complex problem-solving, logical inference, and broad factual recall are areas for potential improvement. Its cost-efficiency and competitive speed are consistent across most benchmarks, making it an economically viable option for its strong suit in classification tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.8
Completion $1.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mancer 2
Mancer 2 | neversleep/llama-3-lumimaid-8b 24K $0.8 / 1M tokens $1.2 / 1M tokens
Featherless
Featherless | neversleep/llama-3-lumimaid-8b 8K $0.8 / 1M tokens $1.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by neversleep