Image-Text-to-Text
Transformers
Safetensors
inkling2_loop
weight-edit
browser-automation
conversational
8-bit precision
modelopt
Instructions to use husky8/Inkling-2-Mini-Fast-Browser-Use with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use husky8/Inkling-2-Mini-Fast-Browser-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-Mini-Fast-Browser-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 AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("husky8/Inkling-2-Mini-Fast-Browser-Use") model = AutoModelForMultimodalLM.from_pretrained("husky8/Inkling-2-Mini-Fast-Browser-Use", device_map="auto") 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?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use husky8/Inkling-2-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-Use
- SGLang
How to use husky8/Inkling-2-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-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-Mini-Fast-Browser-Use with Docker Model Runner:
docker model run hf.co/husky8/Inkling-2-Mini-Fast-Browser-Use
Embed uninterrupted real-time browser runs
Browse files
README.md
CHANGED
|
@@ -8,17 +8,16 @@ tags:
|
|
| 8 |
- browser-automation
|
| 9 |
---
|
| 10 |
|
| 11 |
-
<video controls playsinline preload="metadata" width="100%" poster="https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/resolve/
|
| 12 |
|
| 13 |
## Browser task speedups
|
| 14 |
|
| 15 |
-
Best verified speedup
|
| 16 |
|
| 17 |
| Task | Original Inkling 2 Mini | Edited Inkling 2 Mini | Speedup |
|
| 18 |
|---|---:|---:|---:|
|
| 19 |
| Latest completed order total 路 WebArena 190 | 45.89 s | [5.13 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/686faa4d1748f0120008ec007dc97677678e1643) | **8.95脳** |
|
| 20 |
| Latest canceled order total 路 WebArena 188 | 45.75 s | [6.44 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/cd27dd36403a165685abd5bf202c326ec9590b20) | **7.10脳** |
|
| 21 |
-
| Latest pending order total 路 WebArena 189 | 33.13 s | [5.25 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/686faa4d1748f0120008ec007dc97677678e1643) | **6.31脳** |
|
| 22 |
| Complete an autocomplete field 路 MiniWoB++ seed 103 | 19.86 s | [3.84 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/d4562716ff6d8d0281bf09814a1df0db570f6be3) | **5.18脳** |
|
| 23 |
| Reply to an email 路 MiniWoB++ seed 104 | 26.01 s | [5.98 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/d4562716ff6d8d0281bf09814a1df0db570f6be3) | **4.35脳** |
|
| 24 |
| Search for Xbox 路 WebArena 275 | 20.43 s | [4.96 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/94e67ef0f212bb338d3bff030e48279ab8dd226e) | **4.12脳** |
|
|
@@ -34,6 +33,6 @@ On the completed-order lookup, inference fell from 43.03 s to 2.84 s. The origin
|
|
| 34 |
|
| 35 |
**Weight-space programming.** We edited Inkling 2 Mini鈥檚 output matrix (`model.llm.unembed.weight`) without training. The order checkpoints swap the answer-text and thinking rows (`200004` and `200008`) and adjust the click-command and end-of-generation rows (`34` and `200006`). The completed-order edit changed 9,192 BF16 values. The autocomplete and email runs used the two-row swap available on `main`. [Weight audit](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/evidence/webarena-order-checkpoints/complete-cross/weight-audit.json)
|
| 36 |
|
| 37 |
-
**Method.** The forum post ran on an RTX 5090 with SGLang. The other
|
| 38 |
|
| 39 |
Base model by Thinking Machines Lab. [Inkling 2 Mini](https://huggingface.co/thinkingmachines/Inkling-2-Mini) 路 [Apache 2.0 and modification notice](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/blob/main/NOTICE)
|
|
|
|
| 8 |
- browser-automation
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<video controls playsinline preload="metadata" width="100%" poster="https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/resolve/f86b26e2b3c96c87bbf6de38a84c79382995c665/benchmark/browser-speedups-poster.jpg" src="https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/resolve/f86b26e2b3c96c87bbf6de38a84c79382995c665/benchmark/browser-speedups.mp4"></video>
|
| 12 |
|
| 13 |
## Browser task speedups
|
| 14 |
|
| 15 |
+
Best verified speedup for each of the 12 selected demo tasks across released checkpoints. Both models passed each run shown. Edited times link to the exact weights.
|
| 16 |
|
| 17 |
| Task | Original Inkling 2 Mini | Edited Inkling 2 Mini | Speedup |
|
| 18 |
|---|---:|---:|---:|
|
| 19 |
| Latest completed order total 路 WebArena 190 | 45.89 s | [5.13 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/686faa4d1748f0120008ec007dc97677678e1643) | **8.95脳** |
|
| 20 |
| Latest canceled order total 路 WebArena 188 | 45.75 s | [6.44 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/cd27dd36403a165685abd5bf202c326ec9590b20) | **7.10脳** |
|
|
|
|
| 21 |
| Complete an autocomplete field 路 MiniWoB++ seed 103 | 19.86 s | [3.84 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/d4562716ff6d8d0281bf09814a1df0db570f6be3) | **5.18脳** |
|
| 22 |
| Reply to an email 路 MiniWoB++ seed 104 | 26.01 s | [5.98 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/d4562716ff6d8d0281bf09814a1df0db570f6be3) | **4.35脳** |
|
| 23 |
| Search for Xbox 路 WebArena 275 | 20.43 s | [4.96 s](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/tree/94e67ef0f212bb338d3bff030e48279ab8dd226e) | **4.12脳** |
|
|
|
|
| 33 |
|
| 34 |
**Weight-space programming.** We edited Inkling 2 Mini鈥檚 output matrix (`model.llm.unembed.weight`) without training. The order checkpoints swap the answer-text and thinking rows (`200004` and `200008`) and adjust the click-command and end-of-generation rows (`34` and `200006`). The completed-order edit changed 9,192 BF16 values. The autocomplete and email runs used the two-row swap available on `main`. [Weight audit](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/evidence/webarena-order-checkpoints/complete-cross/weight-audit.json)
|
| 35 |
|
| 36 |
+
**Method.** The forum post ran on an RTX 5090 with SGLang. The other eleven tasks ran on an M5 Max MacBook Pro with MLX. Both models read visible text and numbered controls in Brave. Each pair used the same task, initial page, prompt, greedy decoding, reasoning effort (`none`) and cursor timing. Task time includes inference and browser actions after warmup. We developed the order edits on order-lookup tasks. [WebArena runs](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-ORDER-CHECKPOINTS.md) 路 [MiniWoB++ runs](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/HEADLINERS.md) 路 [Search runs](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-SEARCH-COMMAND.md) 路 [Forum runs](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/WEBARENA-REASONING-CLOSE.md) 路 [Reproduction instructions](https://github.com/jtc268/inkling-2-fast-computer-use/blob/main/benchmark/REPRODUCE-BROWSER.md)
|
| 37 |
|
| 38 |
Base model by Thinking Machines Lab. [Inkling 2 Mini](https://huggingface.co/thinkingmachines/Inkling-2-Mini) 路 [Apache 2.0 and modification notice](https://huggingface.co/husky8/Inkling-2-Mini-Fast-Browser-Use/blob/main/NOTICE)
|