Downloads · 30 days
16
5% of all-time downloads
nishka-gkc-phi3-merged
openpql/nishka-gkc-phi3-merged
nishka-gkc-phi3-merged is a machine learning model from openpql. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Governance Knowledge Corpus model trained on 1.12M tokens of regulatory content across 15 compliance frameworks.
All-time downloads
299
Public
Parameters
3.8B
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- License
- mit
- Model type
- phi3
- Access
- Public
- Created
- Jan 1, 2026
- Updated
- Jan 11, 2026
- SHA
- 8aacc664
Base models
Model card
From the Hugging Face model README
NISHKA GKC
Governance Knowledge Corpus model trained on 1.12M tokens of regulatory content across 15 compliance frameworks.
Model Details
- Base Model: microsoft/Phi-3-mini-4k-instruct
- Architecture: Phi-3 (3.8B parameters)
- Training: LoRA adapter merged into base model
- Format: Full model weights (no adapter needed)
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"openpql/nishka-gkc",
device_map="auto",
torch_dtype="auto",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("openpql/nishka-gkc")
# Generate
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs[0]))
Deployment
This model is ready for deployment with vLLM, TGI, or other inference servers.
# vLLM example
vllm serve openpql/nishka-gkc --dtype float16
- Type
- phi3
- License
- mit
- Languages
- en
- Created
- Jan 1, 2026
- Updated
- Jan 11, 2026