summerwind/llama3

summerwind/ llama3

49 Downloads Updated 2 years ago

Meta Llama 3: The most capable openly available LLM to date.

ollama run summerwind/llama3:8b-instruct-1048k

curl http://localhost:11434/api/chat \
  -d '{
    "model": "summerwind/llama3:8b-instruct-1048k",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='summerwind/llama3:8b-instruct-1048k',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'summerwind/llama3:8b-instruct-1048k',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size / Usage

Context

Input

llama3:8b-instruct-1048k

4.9GB · 1M context window · Text · 2 years ago

llama3:8b-instruct-1048k

4.9GB

Text

llama3:8b-instruct-1048k-q4_K_M

4.9GB · 1M context window · Text · 2 years ago

llama3:8b-instruct-1048k-q4_K_M

4.9GB

Text

llama3:8b-instruct-64k

4.9GB · 62K context window · Text · 2 years ago

llama3:8b-instruct-64k

4.9GB

62K

Text

llama3:8b-instruct-64k-q4_K_M

4.9GB · 62K context window · Text · 2 years ago

llama3:8b-instruct-64k-q4_K_M

4.9GB

62K

Text

Readme

Meta Llama 3: The most capable openly available LLM to date.

Reference

https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-64k