lucataco/deepseek-v3-64k

lucataco/ deepseek-v3-64k

21 Downloads Updated 1 year ago

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

ollama run lucataco/deepseek-v3-64k

curl http://localhost:11434/api/chat \
  -d '{
    "model": "lucataco/deepseek-v3-64k",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='lucataco/deepseek-v3-64k',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'lucataco/deepseek-v3-64k',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size

Context

Input

deepseek-v3-64k:latest

404GB · 160K context window · Text · 1 year ago

deepseek-v3-64k:latest

404GB

160K

Text

Readme

Note: this model requires Ollama 0.5.5 or later.

DeepSeek-V3 achieves a significant breakthrough in inference speed over previous models. It tops the leaderboard among open-source models and rivals the most advanced closed-source models globally.

This is a modified version of deepseek-v3 Q4_K_M with context length set to 64k