Instructions to use TokenBender/glm47-synth-v1-100ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TokenBender/glm47-synth-v1-100ep with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from TokenBender/glm47-synth-v1-100ep: direct link, hf CLI and curl.
- Browser
- Download file 800 Bytes
-
https://huggingface.co/TokenBender/glm47-synth-v1-100ep/resolve/main/README.md
- Command line
-
hf download hf://TokenBender/glm47-synth-v1-100ep/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/TokenBender/glm47-synth-v1-100ep/resolve/main/README.md
800 Bytes
metadata
license: other
base_model: zai-org/GLM-4.7-Flash
library_name: peft
GLM-4.7-Flash Synth v1 SFT checkpoints
All 20 LoRA-r16 checkpoints from the 100-epoch, 8xH100 SFT run are preserved
at five-epoch intervals. Canonical training adapters are under checkpoints/.
The evaluated epoch-5, epoch-50, and epoch-100 checkpoints also include their
derived adapter-serving/ form. The conversion receipt records the exact
removal of auxiliary layer-47 tensors; the canonical adapter is retained.
Base: zai-org/GLM-4.7-Flash at 7dd20894a642a0aa287e9827cb1a1f7f91386b67. Dataset manifest SHA-256:
afec0d05d5c1f9460ac9b2ed4e65aea69775b49639c7ae727f3660308ae1b8b8. See MANIFEST.json for every checkpoint identity and
file hash. Training curves are at the W&B URL recorded in that manifest.