riven/smolvlm

riven/ smolvlm:latest

1,235 Downloads Updated 9 months ago

SmolVLM-500M-Instruct-Q8_0.gguf port

vision

ollama run riven/smolvlm

curl http://localhost:11434/api/chat \
  -d '{
    "model": "riven/smolvlm",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='riven/smolvlm',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'riven/smolvlm',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 9 months ago

9 months ago

4d75b044a6eb · 546MB ·

model

archllama

parameters409M

quantizationQ8_0

437MB

projector

archclip

parameters98.2M

quantizationQ8_0

109MB

params

{ "stop": [ "<|im_end|>" ], "temperature": 0.7, "top_p": 0.9 }

64B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

156B

Readme

A port of ggml-org/SmolVLM-500M-Instruct-GGUF, you may use it with:

curl http://localhost:11434/api/generate -d '{
  "model": "smolvlm",
  "prompt": "What do you see in this image?",
  "images": ["<base64_encoded_image>"]
}'