docs: describe chunked classifier scaffold
Browse files
README.md
CHANGED
|
@@ -27,10 +27,9 @@ Live Space:
|
|
| 27 |
- `https://wchen22-touchdown-compression-classifier.hf.space`
|
| 28 |
- Verified 2026-06-11 with HF CLI: runtime stage `RUNNING`, hardware
|
| 29 |
`cpu-basic`, domain `READY`.
|
| 30 |
-
- The
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
--format json` for the current repo/runtime SHA.
|
| 34 |
- Live smoke:
|
| 35 |
`python3 scripts/smoke_compression_api.py --base-url https://wchen22-touchdown-compression-classifier.hf.space --include-classify --include-batch`
|
| 36 |
validates `/health`, `/v1/classify`, single `/v1/compress`, and managed
|
|
|
|
| 27 |
- `https://wchen22-touchdown-compression-classifier.hf.space`
|
| 28 |
- Verified 2026-06-11 with HF CLI: runtime stage `RUNNING`, hardware
|
| 29 |
`cpu-basic`, domain `READY`.
|
| 30 |
+
- The deployed scaffold supports chunked ONNX artifact inference for long
|
| 31 |
+
prompts. Use `hf spaces info wchen22/touchdown-compression-classifier --format
|
| 32 |
+
json` for the current repo/runtime SHA.
|
|
|
|
| 33 |
- Live smoke:
|
| 34 |
`python3 scripts/smoke_compression_api.py --base-url https://wchen22-touchdown-compression-classifier.hf.space --include-classify --include-batch`
|
| 35 |
validates `/health`, `/v1/classify`, single `/v1/compress`, and managed
|