Using Dolphin 2.6 Mixtral 8x7B on DeepInfra

Quick Start

1. 1
   Create an account at DeepInfra and generate an API key.
2. 2
   Use the DeepInfra SDK or REST API to call dolphin-2.6-mixtral-8x7b — see the documentation for request format.
3. 3
   You'll be billed $0.15/1M input, $0.45/1M output tokens. See full pricing.

Code Examples

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai"
)
response = client.chat.completions.create(
    model="dolphin-2.6-mixtral-8x7b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

About DeepInfra

DeepInfra offers serverless AI inference with a simple API, supporting hundreds of models across text generation, embeddings, and more. Pay-per-token pricing with no upfront commitments.

DeepInfra is a cloud inference platform offering cost-effective access to open-source AI models. It provides serverless inference for leading models from Meta, Mistral, Alibaba, and others with competitive token-based pricing.

Pricing on DeepInfra

Capabilities

No model capability flags are currently sourced.

About Dolphin 2.6 Mixtral 8x7B

Dolphin 2.6 Mixtral 8x7B is a large language model fine-tuned from the Mixtral-8x7B base, known for its robust coding abilities and high compliance with user prompts. Despite not being tuned with Direct Preference Optimization, it performs exceptionally well in coding tasks due to extensive training with coding datasets, including MagiCoder. The model's architecture features a context window reduced to 16k, and training was carried out using techniques like qLoRA. However, it is uncensored, exposing potential ethical concerns and prompting caution for deployment without additional safeguards. Quantized versions are available to accommodate different hardware needs, and users may encounter variation in performance with larger context windows.