Downloads · 30 days
6
18% of all-time downloads
granite-3.3-8b-cuad-lora
harpreet22happy/granite-3.3-8b-cuad-lora
granite-3.3-8b-cuad-lora is a machine learning model from harpreet22happy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter for ibm-granite/granite-3.3-8b-instruct, trained on the cuad long-document task at up to 24576 tokens per example (finetuneexperiments/task3/ in the source repo: govreport = report - summary, kleister = c…
All-time downloads
34
Public
Repo size
396 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors198 MB · 98%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 4b608c1b
Base models
Model card
From the Hugging Face model README
cuad long-context SFT LoRA
LoRA adapter for ibm-granite/granite-3.3-8b-instruct, trained on the cuad long-document task at up to
24576 tokens per example (fine_tune_experiments/task3/ in the source repo:
govreport = report -> summary, kleister = charity report -> 8-field JSON, cuad = contract ->
41-category clause JSON). main = best checkpoint by held-out loss; branch final = last.
Stage: SFT.
- LoRA: r=16, alpha=32, target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
- bf16, FlashAttention-2 + padding-free packing, completion-only loss (report masked, summary supervised)
This branch: checkpoint-50 (dev loss 0.0442, the minimum of 5 evals).
Dev loss by step: 10: 0.0632, 20: 0.0520, 30: 0.0470, 40: 0.0446, 50: 0.0442
- Library
- peft
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026