Dolphin 2.6 Mixtral 8x7B 🐬 Check detailed information and pricing for AI models
Context Length 32,768 tokens, cognitivecomputations from provided
32,768
Context Tokens
$0.00
Prompt Price
$0.00
Output Price
0/16
Feature Support
Model Overview
This is a 16k context fine-tune of [Mixtral-8x7b](/models/mistralai/mixtral-8x7b). It excels in coding tasks due to extensive training with coding data and is known for its obedience, although it lacks DPO tuning. 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
Basic Information
Developer
cognitivecomputations
Model Series
Mistral
Release Date
2023-12-21
Context Length
32,768 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.00 / 1M tokens
Completion Tokens
$0.00 / 1M tokens
Supported Features
Unsupported (16)
Image Input
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Reasoning
Web Search Options
Top A