Author's Description
Lumimaid v0.2 70B is a finetune of [Llama 3.1 70B](/meta-llama/llama-3.1-70b-instruct) with a "HUGE step up dataset wise" compared to Lumimaid v0.1. Sloppy chats output were purged. 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: Lumimaid v0.2 70B demonstrates moderate speed performance, ranking in the 21st percentile across benchmarks, indicating it is not among the fastest models available. Its pricing is also moderate, placing it in the 23rd percentile, suggesting it offers competitive but not exceptionally low costs. A standout feature is its exceptional reliability, achieving the 99th percentile, meaning it consistently provides usable responses with minimal technical failures. In terms of specific performance, Lumimaid v0.2 excels in classification tasks, achieving perfect 100% accuracy in Email Classification, making it the most accurate model at its price point and among models of similar speed. This highlights a significant strength in precise categorization. While its General Knowledge accuracy is strong at 95%, its duration for this task is notably high, placing it in the 9th percentile for speed. Performance in Reasoning and Ethics is moderate, with 58% and 98% accuracy respectively, indicating room for improvement in complex problem-solving and nuanced ethical scenarios compared to its classification prowess. Overall, its key strength lies in highly accurate and reliable classification, while speed and advanced reasoning remain areas for potential enhancement.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $2.5 |
Completion | $3 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Mancer 2
|
Mancer 2 | neversleep/llama-3.1-lumimaid-70b | 16K | $2.5 / 1M tokens | $3 / 1M tokens |
Featherless
|
Featherless | neversleep/llama-3.1-lumimaid-70b | 16K | $2.5 / 1M tokens | $3 / 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 8B | Sep 14, 2024 | 8B | 32K |
Text input
Text output
|
★★★ | ★ | $$$ |
NeverSleep: Llama 3 Lumimaid 70B | May 15, 2024 | 70B | 8K |
Text input
Text output
|
★ | ★ | $$$$$ |
NeverSleep: Llama 3 Lumimaid 8B Unavailable | May 03, 2024 | 8B | 24K |
Text input
Text output
|
★★★ | ★★ | $$$ |
Noromaid 20B | Nov 25, 2023 | 20B | 8K |
Text input
Text output
|
★★ | ★ | $$$$ |