Fimbulvetr 11B v2

Text input Text output Unavailable
Author's Description

Creative writing model, routed with permission. It's fast, it keeps the conversation going, and it stays in character. If you submit a raw prompt, you can use Alpaca or Vicuna formats.

Key Specifications
Cost
$$$$
Context
4K
Parameters
300B
Released
Apr 20, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

Fimbulvetr 11B v2, a creative writing model, demonstrates exceptional speed and competitive pricing. It consistently ranks among the fastest models and offers among the most competitive pricing across five benchmarks. In terms of performance across categories, the model exhibits a notable strength in Email Classification, achieving 97.0% accuracy, placing it in the 46th percentile. This suggests a strong capability in understanding context and purpose for categorization tasks. However, its performance in other areas is less robust. General Knowledge yielded 62.0% accuracy (18th percentile), and Ethics scored 33.0% accuracy (12th percentile), indicating significant room for improvement in these domains. Instruction Following also presented a weakness with 21.3% accuracy (26th percentile). A critical area of concern is Coding, where the model achieved 0.0% accuracy, suggesting it is not suitable for programming-related tasks. The model's duration metrics are generally in the lower percentiles, aligning with its high-speed ranking.

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)
Featherless
Featherless | sao10k/fimbulvetr-11b-v2 4K $0.8 / 1M tokens $1.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by sao10k