Intern-Decision-2B, compiled for the browser

InternLM's Intern-Decision-2B compiled into a fusor-ai bundle: the weights the browser runtime of intern-decision-wasm loads to answer questions with calibrated probabilities on the device's CPU. Try it in the Space fusorlabs/intern-decision-wasm.

  • Source: internlm/Intern-Decision-2B at revision 85c5657708a09884ff9fd8d7f57789b410a97b33, compiled with the mix profile: 4-bit feed-forwards, everything else 7-bit (2068 MB).
  • Format: manifest.json lists every tensor and part; each part is named by its BLAKE3 hash, which the runtime checks as it loads.
  • Reproduce it: just model in intern-decision-wasm downloads the checkpoint and compiles the same bundle.

This is not a PyTorch or safetensors checkpoint: it only loads in the intern-decision-wasm runtime.

The model is Apache-2.0 (LICENSE), built on Qwen3.5 (LICENSE-QWEN).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for fusorlabs/intern-decision-2b-web

Finetuned
Qwen/Qwen3.5-2B
Finetuned
(1)
this model

Space using fusorlabs/intern-decision-2b-web 1