Noromaid 20B

Text input Text output
Author's Description

A collab between IkariDev and Undi. This merge is suitable for RP, ERP, and general knowledge. #merge #uncensored

Key Specifications
Cost
$$$$
Context
8K
Parameters
20B
Released
Nov 25, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logit Bias Structured Outputs Response Format Stop Seed Min P Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Features

This model supports the following features:

Response Format Structured Outputs
Performance Summary

Noromaid 20B, a collaboration between IkariDev and Undi, demonstrates exceptional performance in terms of operational efficiency. It consistently ranks among the fastest models available and offers highly competitive pricing, placing it in the Infinityth percentile for both speed and cost across eight benchmarks. This makes it a very attractive option for cost-sensitive and high-throughput applications. However, the model's accuracy across various benchmarks indicates significant limitations in its current capabilities. While it achieves a respectable 94.0% accuracy in Email Classification, suggesting a strength in contextual understanding for specific categorization tasks, its performance in other areas is notably low. It struggles significantly with General Knowledge (0.5% accuracy), Ethics (10.0% accuracy), Instruction Following (2.0% accuracy), and Coding (5.0% accuracy). Furthermore, it scored 0.0% accuracy in both Mathematics and Reasoning, indicating a fundamental weakness in complex problem-solving and logical deduction. Its 44.0% accuracy in Hallucinations suggests it sometimes struggles to appropriately acknowledge uncertainty. Overall, Noromaid 20B excels in operational efficiency but requires substantial improvement in its core intellectual capabilities for general-purpose applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1
Completion $1.75

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Mancer 2
Mancer 2 | neversleep/noromaid-20b 8K $1 / 1M tokens $1.75 / 1M tokens
NextBit
NextBit | neversleep/noromaid-20b 4K $1 / 1M tokens $1.75 / 1M tokens
Mancer 2
Mancer 2 | neversleep/noromaid-20b 8K $1 / 1M tokens $2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by neversleep