Challenging the limit of 464M params

ollama run DiamondGotCat/Zeta-4:i1-Q5_K_S

curl http://localhost:11434/api/chat \
  -d '{
    "model": "DiamondGotCat/Zeta-4:i1-Q5_K_S",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='DiamondGotCat/Zeta-4:i1-Q5_K_S',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'DiamondGotCat/Zeta-4:i1-Q5_K_S',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 8 months ago

8 months ago

5e80370eeee2 · 346MB ·

model

archqwen2

parameters464M

quantizationQ5_K_S

346MB

template

{{ if .System }}{{ .System }}{{ end }} {{ if .Prompt }}<USER>{{ .Prompt }}</USER>{{ end }} <ASSISTAN

102B

params

{ "stop": [ "</ASSISTANT>" ] }

36B

Readme

Challenging the limit of 464M params: Zeta 4

Models

Prompt Template

{{ if .System }}{{ .System }}{{ end }}
{{ if .Prompt }}<USER>{{ .Prompt }}</USER>{{ end }}
<ASSISTANT>

Stop Token

</ASSISTANT>

Computer Spec

Machine: RunPod VM(GPU, NVIDIA A100 PCIe)

Dataset

Details of the dataset used can be found here

Links

GitHub: Zeta

Zeta is just a small SLM. But don’t forget that it has big dreams inside.