Image-Text-to-Text
Transformers
Safetensors
inkling2_loop
text-generation
weight-edit
browser-automation
conversational
8-bit precision
modelopt
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
Report browser timings by device model and link paired results
Browse files
README.md
CHANGED
|
@@ -10,13 +10,15 @@ tags:
|
|
| 10 |
|
| 11 |
# Inkling 2 Fast Browser Use
|
| 12 |
|
|
|
|
|
|
|
| 13 |
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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/FORM-CART-RECHECK.md)
|
| 14 |
|
| 15 |
-
A separate four-row checkpoint passed WebArena search task 274
|
| 16 |
|
| 17 |
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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-10.md).
|
| 18 |
|
| 19 |
-
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
|
| 20 |
|
| 21 |
## BrowserGym
|
| 22 |
|
|
|
|
| 10 |
|
| 11 |
# Inkling 2 Fast Browser Use
|
| 12 |
|
| 13 |
+
**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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/a5f603d64000d1375b383f44b2b9bc55616b491a/benchmark/HEADLINERS.md) · [Watch the comparisons at 1×](https://jtc268.github.io/inkling-2-fast-computer-use/)
|
| 14 |
+
|
| 15 |
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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/FORM-CART-RECHECK.md)
|
| 16 |
|
| 17 |
+
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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-SEARCH.md) · [Four-row checkpoint](https://huggingface.co/husky8/Inkling-2-Fast-Computer-Use/tree/fa1ef63d66ec9d489dc185cd0a8ca5452a28bfe9)
|
| 18 |
|
| 19 |
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](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-10.md).
|
| 20 |
|
| 21 |
+
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.
|
| 22 |
|
| 23 |
## BrowserGym
|
| 24 |
|