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
Supported Parameters
This model supports the following parameters:
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
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
NeverSleep: Lumimaid v0.2 70B Unavailable | Oct 21, 2024 | 70B | 16K |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
NeverSleep: Lumimaid v0.2 8B | Sep 14, 2024 | 8B | 32K |
Text input
Text output
|
★★★ | ★ | $$$ |
NeverSleep: Llama 3 Lumimaid 70B | May 15, 2024 | 70B | 8K |
Text input
Text output
|
★ | ★ | $$$$$ |
Noromaid 20B | Nov 25, 2023 | 20B | 8K |
Text input
Text output
|
★★ | ★ | $$$$ |