Llama2 Merged 4bit ALL 67k R64 3e

Overview

Llama2 Merged 4bit ALL 67k R64 3e is a efficient model from Featherless with a 4K context window. Available through ANT's unified API.

ANT Routing Intelligence

Limited routing data available for Llama2 Merged 4bit ALL 67k R64 3e. Intelligence insights will appear as more requests are routed through ANT.

Quick Start

from openai import OpenAI

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

response = client.chat.completions.create(
    model="featherless/karsar/Llama2_merged_4bit_ALL_67k_r64_3e",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Try it or ask an AI