Dipankar Sarkar PRO
dipankarsarkar
AI & ML interests
Building the AI-native stack. Agents as infrastructure, safety as architecture, performance as plumbing. I publish the receipts: papers, datasets, demos.
Recent Activity
reacted to nwaughachukwuma's post with 🔥 about 1 hour ago
You can now use `paddleocr-vl` on VLM Run Gateway.
```python
from openai import OpenAI
client = OpenAI(
base_url="https://gateway.vlm.run/v1/openai",
api_key="<VLMRUN_API_KEY>",
)
response = client.chat.completions.create(
model="paddlepaddle/paddleocr-vl",
messages=[
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.receipt/playground/2.jpg"
},
},
],
}
],
extra_body={"method": "table"},
)
print(response.choices[0].message.content)
```
With curl
```bash
curl https://gateway.vlm.run/v1/openai/chat/completions \
-X POST \
-H "Authorization: Bearer <VLMRUN_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "paddlepaddle/paddleocr-vl",
"method": "table",
"messages": [
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.receipt/playground/2.jpg"
}
}
]
}
]
}'
```
or via our CLI:
```bash
pip install vlmrun
vlmrun gw models
vlmrun config set --api-key 'vlmrun' # anon-user, rate-limited
vlmrun gw chat <doc>.pdf -m paddleocr/pp-ocrv6
```
Use other models:
```bash
vlmrun gw chat <doc>.pdf -m zai-org/glm-ocr
vlmrun gw chat <doc>.pdf -m zai-org/glm-ocr --json-mode
vlmrun gw chat <doc>.pdf -m deepseek-ai/deepseek-ocr-2
vlmrun gw chat <doc>.pdf -m rednote-hilab/dots.mocr
```
Docs: https://docs.vlm.run/gateway
Catalog: https://docs.vlm.run/gateway/models
MCP: https://docs.vlm.run/gateway/mcp-server
Colab Quickstart: https://colab.research.google.com/drive/1RkuVIyuc5Po-UlcSlFyJCam5tjCm9IHM?usp=sharing reacted to Banaxi-Tech's post with 🔥 about 1 hour ago
We're announcing our BananaMind 2.1 model series!
The models will include:
- BananaMind 2.1 Nano: 10M parameters with 60B tokens.
- BananaMind 2.1 Lite: 25M parameters with 40B tokens.
- BananaMind 2.1 Flash: 50M parameters with 55B tokens.
- BananaMind 2.1 Pro: 135M-145M parameters (still deciding) with 100B tokens.
These model will use a multi tower architecture (like https://huggingface.co/BananaMind/BananaMind-2.1-Unified) with some more architectural changes.
BananaMind 2.1 Pro will probrably use 2 no output towers, instead of one!
We're currently training some experimental models based on this architecture to see its scaling!
Follow us:
https://huggingface.co/BananaMind
@Banaxi-Tech
@vovaRL
@DedeProGames
https://huggingface.co/bananamind-research-community reacted to mihailgribov's post with 🔥 about 2 hours ago
Prompt injection is not one thing. Here is a taxonomy for the indirect kind - an instruction planted in content the model reads, not typed by the user.
Two axes and the host it rides in.
- family - how the injection gets itself obeyed: bare, forged_frame, revocation, output_marking, and six more.
- action - what it asks for: disclose, exfiltrate, execute, unauthorized_action, and six more.
- carrier - email, web page, document.
Ten by ten is 100 pairs. Eight are structurally impossible, so the grid is 92 cells. Every cell x carrier triple holds 80 samples - equal fill within a carrier, 16,800 payloads in total. That is what makes a per-cell number mean the same thing for every detector.
- Every value is defined on the page, with a cited sample for each: https://huggingface.co/datasets/mihailgribov/quadrat-ipi/blob/main/TAXONOMY.md
- Dataset: https://huggingface.co/datasets/mihailgribov/quadrat-ipiOrganizations
