Instructions to use husky8/Inkling-2-Fast-Computer-Use with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use husky8/Inkling-2-Fast-Computer-Use with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="husky8/Inkling-2-Fast-Computer-Use") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("husky8/Inkling-2-Fast-Computer-Use", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use husky8/Inkling-2-Fast-Computer-Use with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "husky8/Inkling-2-Fast-Computer-Use" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Fast-Computer-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/husky8/Inkling-2-Fast-Computer-Use
- SGLang
How to use husky8/Inkling-2-Fast-Computer-Use with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "husky8/Inkling-2-Fast-Computer-Use" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Fast-Computer-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "husky8/Inkling-2-Fast-Computer-Use" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "husky8/Inkling-2-Fast-Computer-Use", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use husky8/Inkling-2-Fast-Computer-Use with Docker Model Runner:
docker model run hf.co/husky8/Inkling-2-Fast-Computer-Use
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("husky8/Inkling-2-Fast-Computer-Use", device_map="auto")Inkling 2 Fast Browser Use
5.18× on one autocomplete case. Original Inkling 2 Mini 19.86 s, two-row edit 3.84 s, both passed on M5 Max MacBook Pro. The same case on the M5 Max MacBook Pro measured 15.46 → 3.36 s in the independent video retake (12.11 seconds saved). On the original 20-case MiniWoB++ panel the original passed 11/20 and the edit passed 6/20. Work in progress. Run receipts and hardware record · Watch the comparisons at 1×
A fresh six-case run of this two-row checkpoint on the MacBook Pro measured 2.39× end to end, compared with 2.56× in the first run. On the repeat the edit passed 6/6, the original passed 4/6, and median time on the four common successes fell from 16.62 s to 6.96 s. The same filmed case measured 1.03× on one RTX 5090. All attempts and fresh video
A separate four-row checkpoint passed WebArena search task 274 in paired RTX 5090 runs, with observed wall-time speedups of 1.52×, 1.54× and 1.55×. Search results · Four-row checkpoint
This project measures browser tasks in Brave. The Mac form-and-cart checkpoint and the RTX 5090 WebArena checkpoint are separate edits. Ten WebArena results.
This checkpoint swaps two rows in Inkling 2 Mini’s output layer. On six paired Brave runs, the model filled a form and added the requested quantity to a cart in a median of 7.93 seconds, down from 20.34 seconds. Both checkpoints completed all six runs with identical commands. The test ran on an M5 Max MacBook Pro using MLX and text descriptions of visible controls. Screenshot-based control and other browsers are untested.
BrowserGym
The original passed 11/20 cases and the edit passed 6/20. Both passed 5. The original alone passed 6, the edit alone passed 1, and both failed 8. Across the 5 joint successes, median completion time was 19.86 s original and 3.84 s edited. Four paired seeds per environment. Task scores and receipts
Download
hf download husky8/Inkling-2-Fast-Computer-Use --local-dir inkling-browser
In an Inkling-compatible computer-use agent, select husky8/Inkling-2-Fast-Computer-Use as the model. The agent still supplies observations and executes actions. The full checkpoint is about 20 GB. Load the directory with a runtime that supports the original Inkling 2 Mini format. Benchmark, video and runnable example
Weight change
Rows 200004 and 200008 of model.llm.unembed.weight exchanged places. These rows score the answer and thinking channel markers. On this task the edit eliminated generated thinking tokens. Both checkpoints used greedy decoding and reasoning effort none. In a separate development run, prefilling the original checkpoint’s answer channel also produced a similar time. General reasoning and visual accuracy after this edit have not been evaluated.
Base revision ed40e7da625f594fc9c4990f5f66be24873c22d7. Edited shard SHA-256 d713d16818032b5ac0d06b07e72d4dc7135d57737e3224216d09b51afe59ab6e.
Independent modification of Thinking Machines Lab’s Inkling 2 Mini, distributed under Apache 2.0. Original model card · Model acceptable use policy · Modification notice
- Downloads last month
- -
Model tree for husky8/Inkling-2-Fast-Computer-Use
Base model
thinkingmachines/Inkling-2-Mini
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="husky8/Inkling-2-Fast-Computer-Use") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)