ReMM SLERP 13B

Text input Text output
Author's Description

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

Key Specifications
Cost
$$$$
Context
4K
Parameters
13B
Released
Jul 21, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

ReMM SLERP 13B, provided by undi95, demonstrates exceptional speed and cost efficiency. It consistently ranks among the fastest models and offers highly competitive pricing, achieving Infinityth percentile rankings across multiple benchmarks for both speed and price. This makes it a strong contender for applications where rapid processing and cost-effectiveness are paramount. However, the model's accuracy across various benchmarks indicates significant areas for improvement. In Coding, it achieved only 1.0% accuracy, placing it in the 8th percentile. Instruction Following showed 0.0% accuracy, suggesting a fundamental limitation in processing complex directives. Similarly, Reasoning (16.0% accuracy, 11th percentile), Ethics (2.0% accuracy, 7th percentile), and General Knowledge (0.5% accuracy, 10th percentile) all performed at very low percentiles. The Email Classification benchmark was a notable exception, achieving 90.0% accuracy, though still only at the 17th percentile. Its primary strength lies in its operational efficiency (speed and cost), while its key weakness is its low accuracy across most cognitive and knowledge-based tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.5
Completion $0.75

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Featherless
Featherless | undi95/remm-slerp-l2-13b 4K $0.5 / 1M tokens $0.75 / 1M tokens
Mancer 2
Mancer 2 | undi95/remm-slerp-l2-13b 6K $0.5 / 1M tokens $0.75 / 1M tokens
NextBit
NextBit | undi95/remm-slerp-l2-13b 6K $0.7 / 1M tokens $1 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by undi95