AI-TAVS/Agents-A1-vision:4b

AI-TAVS/ Agents-A1-vision:4b

67 Downloads Updated 1 month ago

Agents-A1: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent.

vision 4b 35b

ollama run AI-TAVS/Agents-A1-vision:4b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "AI-TAVS/Agents-A1-vision:4b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='AI-TAVS/Agents-A1-vision:4b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'AI-TAVS/Agents-A1-vision:4b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

05bea6e3cad4 · 5.2GB ·

model

archqwen35

parameters4.21B

quantizationQ8_0

4.5GB

projector

archclip

parameters334M

quantizationF16

672MB

template

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

181B

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

Readme

Agents‑A1 is a 35B Mixture‑of‑Experts agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities.

Detail: https://huggingface.co/InternScience/Agents-A1-Q4_K_M-GGUF