HiTOP Llama 3B 4bit is a efficient model from Featherless with a 33K context window. Available through ANT's unified API.
Limited routing data available for HiTOP Llama 3B 4bit. Intelligence insights will appear as more requests are routed through ANT.
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/FritzStack/HiTOP-Llama-3B_4bit",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Unlearn Tofu Llama 3.2 1B Instruct Forget10 RMU Lr5e 05 Layer5 Scoeff10 Epoch10
Zyte 1B
Llama 2 New Ontology V2.1
Llama 3 Tulu 2 70b
DmWM Llama 3.2 1B Instruct HarmData Al4 OWT D4 A0.25
Mistral 7b V0.3
CompassJudger 1 14B Instruct
Finetuned Gemma 2 2b Output Layer 20 16k 4