SorcererLM 8x22B

Text input Text output
Author's Description

SorcererLM is an advanced RP and storytelling model, built as a Low-rank 16-bit LoRA fine-tuned on [WizardLM-2 8x22B](/microsoft/wizardlm-2-8x22b). - Advanced reasoning and emotional intelligence for engaging and immersive interactions - Vivid writing capabilities enriched with spatial and contextual awareness - Enhanced narrative depth, promoting creative and dynamic storytelling

Key Specifications
Cost
$$$$$
Context
16K
Parameters
22B
Released
Nov 08, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

SorcererLM 8x22B, provided by raifle and created on November 8, 2024, is an advanced RP and storytelling model fine-tuned on WizardLM-2 8x22B. It demonstrates competitive response times, performing among the faster models with a speed ranking in the 47th percentile. However, it is positioned at premium pricing levels, ranking in the 18th percentile for cost competitiveness. The model's core strengths lie in its intended use case, emphasizing advanced reasoning, emotional intelligence, vivid writing, and enhanced narrative depth. Across benchmarks, SorcererLM 8x22B shows varied performance. It achieved a respectable 96.0% accuracy in Email Classification, indicating strong contextual understanding for categorization tasks. Its Reasoning and Ethics capabilities, at 42.0% and 75.0% accuracy respectively, suggest room for improvement in complex problem-solving and nuanced ethical dilemmas. A notable weakness is its General Knowledge, scoring only 37.0% accuracy, which may limit its utility in tasks requiring broad factual recall. While its speed is competitive, the higher cost across all benchmarks, particularly for the Email Classification task, suggests that its premium pricing might not always align with its accuracy performance in certain domains.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $4.5
Completion $4.5

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Infermatic
Infermatic | raifle/sorcererlm-8x22b 16K $4.5 / 1M tokens $4.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration