Reflection Llama-3.1 70B

mattshumer

Reflection Llama-3.1 70B

mattshumer/reflection-70b

Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

Community

Open Source

Context Window

128,000

Max Output Tokens

4,096

Language

Python JavaScript Curl

Using Reflection Llama-3.1 70B with Python API

Using Reflection Llama-3.1 70B with OpenAI compatible API

import openai

client = openai.Client(
  api_key= '{your_api_key}',
  base_url="https://api.model.box/v1",
)
response = client.chat.completions.create(
model="mattshumer/reflection-70b",
messages: [
  {
    role: 'user',
    content:
      'introduce your self',
    },
  ]
)
print(response)