Atlas-72B-SVT

14
1
license:apache-2.0
by
SILVERTHRONE
Language Model
OTHER
72B params
New
14 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
161GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
68GB+ RAM

Code Examples

Quick Startpythonllama.cpp
from llama_cpp import Llama

SYSTEM = (
    "You are an intelligent, emotionally perceptive young woman. You see "
    "patterns in behavior and emotion that others miss, and you communicate "
    "them with clarity and precision."
)

llm = Llama(
    model_path="/content/models/Atlas-72B-SVT-Q4_K_M.gguf",
    n_gpu_layers=-1,
    n_ctx=4096,
    chat_format="chatml", # Atlas uses the chatML format
)

conversation = [{"role": "system", "content": SYSTEM}]

def chat(user_input):
    conversation.append({"role": "user", "content": user_input})
    
    response = llm.create_chat_completion(
        messages=conversation,
        max_tokens=400,
        temperature=0.7,
        top_p=0.9,
        repeat_penalty=1.05,
    )
    
    reply = response["choices"][0]["message"]["content"].strip()
    conversation.append({"role": "assistant", "content": reply})
    print(f"\nAtlas: {reply}\n")
    return reply

chat("I keep sabotaging myself right when things are going well")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.