8 lines
248 B
Markdown
8 lines
248 B
Markdown
|
---
|
||
|
|
license: mit
|
||
|
|
---
|
||
|
|
|
||
|
|
# R1-Distill-Qwen-7B-AWQ — offline inference bundle
|
||
|
|
|
||
|
|
AWQ 4-bit reasoning model with a self-contained script.py that runs fully offline (loads from `.`). Reasons step by step, then emits a final JSON array. Fits a 16 GB GPU.
|