51 lines
1.1 KiB
Markdown
51 lines
1.1 KiB
Markdown
---
|
|
license: mit
|
|
language:
|
|
- en
|
|
tags:
|
|
- pql
|
|
- compliance
|
|
- governance
|
|
- phi-3
|
|
base_model: microsoft/Phi-3-mini-4k-instruct
|
|
---
|
|
|
|
# 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
|
|
|
|
```python
|
|
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.
|
|
|
|
```bash
|
|
# vLLM example
|
|
vllm serve openpql/nishka-gkc --dtype float16
|
|
```
|