Dolphin 2.9.2 Mixtral 8x22B 🐬

Text input Text output
Author's Description

Dolphin 2.9 is designed for instruction following, conversational, and coding. This model is a finetune of [Mixtral 8x22B Instruct](/models/mistralai/mixtral-8x22b-instruct). It features a 64k context length and was fine-tuned with a 16k sequence length using ChatML templates. This model is a successor to [Dolphin Mixtral 8x7B](/models/cognitivecomputations/dolphin-mixtral-8x7b). The model is uncensored and is stripped of alignment and bias. It requires an external alignment layer for ethical use. Users are cautioned to use this highly compliant model responsibly, as detailed in a blog post about uncensored models at [erichartford.com/uncensored-models](https://erichartford.com/uncensored-models). #moe #uncensored

Key Specifications
Cost
$$$$
Context
16K
Parameters
22B
Released
Jun 07, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

Dolphin 2.9.2 Mixtral 8x22B demonstrates moderate speed performance, ranking in the 30th percentile across benchmarks, indicating it is not among the fastest models available. Its pricing is also moderate, placing it in the 38th percentile, suggesting it offers competitive but not exceptionally low costs. A standout feature is its exceptional reliability, achieving a perfect 100th percentile, meaning it consistently provides usable responses with minimal technical failures. In terms of specific performance, the model achieved 95.0% accuracy in Email Classification, showing strong capability in this domain, though its percentile rank (34th) suggests other models may perform better. Its Reasoning abilities are a notable weakness, with only 40.0% accuracy (25th percentile). The model performs well in Ethics, scoring 99.0% accuracy (59th percentile), indicating a robust understanding of ethical principles. However, its General Knowledge is a significant area for improvement, with 71.0% accuracy (22nd percentile), suggesting a limited grasp of broad factual information. Overall, Dolphin 2.9.2 excels in reliability and specific classification tasks, but its reasoning and general knowledge capabilities present clear areas for enhancement.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.9
Completion $0.9

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Novita
Novita | cognitivecomputations/dolphin-mixtral-8x22b 16K $0.9 / 1M tokens $0.9 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by cognitivecomputations