Jainamshahhh commited on
Commit
dfcbee9
·
verified ·
1 Parent(s): d56cada

README: note Modal usage (Best Use of Modal sponsor prize)

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -43,6 +43,15 @@ B judge panel · 1–5 sparring bots · 7 the Masher · 8 the Executioner ·
43
  *(This Space is a `gradio.Server` app — Gradio's engine serves the custom canvas at `/`,
44
  and the `trace_digest` endpoint runs through Gradio's queue, callable with `gradio_client`.)*
45
 
 
 
 
 
 
 
 
 
 
46
  ## 🎖️ Badge artifacts (everything is public)
47
 
48
  | Badge | Evidence |
 
43
  *(This Space is a `gradio.Server` app — Gradio's engine serves the custom canvas at `/`,
44
  and the `trace_digest` endpoint runs through Gradio's queue, callable with `gradio_client`.)*
45
 
46
+ ## ⚡ Built with Modal
47
+
48
+ The entire model program ran on **[Modal](https://modal.com)**: all six fine-tune
49
+ generations (TRL behavior-cloning on A100s), every evaluation and the
50
+ classifier-free-guidance sweep, the GGUF conversion (llama.cpp), and the vLLM
51
+ CFG inference gateway. The published fine-tune that ships in this app was trained,
52
+ evaluated, and converted end-to-end on Modal — comfortably inside the $250 credit
53
+ grant. Recipe + reproduce commands: [model card](https://huggingface.co/Jainamshahhh/parry-tactician-1.5b-merged).
54
+
55
  ## 🎖️ Badge artifacts (everything is public)
56
 
57
  | Badge | Evidence |