robit/ornith-1.5:9b

robit/ ornith-1.5:9b

110 Downloads Updated 1 week ago

Ornith-1.5 Vision + Tools + Thinking, a major step toward building foundation models through end-to-end self-improvement.

vision tools thinking 9b

ollama run robit/ornith-1.5:9b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "robit/ornith-1.5:9b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='robit/ornith-1.5:9b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'robit/ornith-1.5:9b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 week ago

1 week ago

4b67623d455e · 6.6GB ·

model

archqwen35

parameters8.95B

quantizationQ4_K_M

5.6GB

projector

archclip

parameters456M

quantizationBF16

922MB

template

13B

license

1.1kB

params

{ "min_p": 0, "num_ctx": 262144, "num_predict": 16384, "presence_penalty": 1.5,

163B

Readme

Added Thinking + Tools to base Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

Ornith-1.5 extends Ornith-1.0 by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For more details on the task, harness, and rollout reward design, please refer to our blog.

Ornith-1.5-9B