Dolphin 2.6 Mixtral 8x7B 🐬

cognitivecomputations/dolphin-mixtral-8x7b

33KContext Window

Normal

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

Capabilities

Text GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Input Token< ¥0.001/1K Token

Output Token< ¥0.001/1K Token

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="cognitivecomputations/dolphin-mixtral-8x7b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)