llama-pro:8b-instruct-q2

llama-pro:8b-instruct-q2_K

237.7K Downloads Updated 2 years ago

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

ollama run llama-pro:8b-instruct-q2_K

curl http://localhost:11434/api/chat \
  -d '{
    "model": "llama-pro:8b-instruct-q2_K",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='llama-pro:8b-instruct-q2_K',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'llama-pro:8b-instruct-q2_K',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

24ca2680af67 · 3.5GB ·

model

archllama

parameters8.36B

quantizationQ2_K

3.5GB

params

{ "stop": [ "<|system|>", "<|user|>", "<|assistant|>" ] }

81B

template

<|system|> {{ .System }} <|user|> {{ .Prompt }} <|assistant|>

62B

Readme

LLaMa-Pro is a version of the original LLaMa model enhanced by the addition of transformer blocks by Tencent Applied Research Center (ARC). This model specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

References

GitHub

Hugging Face