Instructions to use Kushalkhemka/CyberOSS-CVE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kushalkhemka/CyberOSS-CVE with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Kushalkhemka/CyberOSS-CVE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kushalkhemka/CyberOSS-CVE")
model = AutoModelForCausalLM.from_pretrained("Kushalkhemka/CyberOSS-CVE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kushalkhemka/CyberOSS-CVE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kushalkhemka/CyberOSS-CVE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kushalkhemka/CyberOSS-CVE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kushalkhemka/CyberOSS-CVE

SGLang

How to use Kushalkhemka/CyberOSS-CVE with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Kushalkhemka/CyberOSS-CVE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kushalkhemka/CyberOSS-CVE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Kushalkhemka/CyberOSS-CVE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kushalkhemka/CyberOSS-CVE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kushalkhemka/CyberOSS-CVE with Docker Model Runner:
```
docker model run hf.co/Kushalkhemka/CyberOSS-CVE
```

CyberOSS-CVE / README.md

Kushalkhemka

Add HF metadata for usage menu

d0372f5 verified 6 months ago

preview code

raw

history blame contribute delete

2.15 kB

metadata

language:
  - en
license: lgpl-3.0
tags:
  - text-generation
  - gpt-oss
  - cybersecurity
  - vllm
base_model: unsloth/gpt-oss-20b-BF16
libraries:
  - transformers
library_name: transformers
model_type: gpt_oss
pipeline_tag: text-generation
datasets:
  - AlicanKiraz0/All-CVE-Records-Training-Dataset

CyberOSS-CVE

Fine-tuned gpt-oss-20b on the AlicanKiraz0/All-CVE-Records-Training-Dataset using Unsloth with LoRA (rank 32) and merged back to BF16 for compatibility with vLLM, Hugging Face Transformers, and GGUF conversions.

Training Overview

Base model: unsloth/gpt-oss-20b-BF16
Dataset: AlicanKiraz0/All-CVE-Records-Training-Dataset
Hardware: single NVIDIA H100 80GB
Sequence length: 2048
Batch: 2 (grad accum 4 → effective 8)
Learning rate: 2e-4, linear warmup 5 steps
Steps: 100 for quick verification run (expand for full epoch)
Loss masking: full conversation (system, user, assistant)

Files

model-0000X-of-00009.safetensors: merged BF16 shards
config.json: GPT-OSS architecture config
tokenizer.json and template: Harmony/GPT-OSS chat format
chat_template.jinja: OpenAI Harmony-compatible chat template

Quick Usage (vLLM)

pip install vllm==0.11.2 transformers==4.57.2
python - <<'PY'
from vllm import LLM, SamplingParams
from transformers.processing_utils import ProcessorMixin
import transformers
transformers.ProcessorMixin = ProcessorMixin

llm = LLM(
    model="Kushalkhemka/CyberOSS-CVE",
    tokenizer="unsloth/gpt-oss-20b-BF16",
    dtype="bfloat16",
)
prompt = "You are a cybersecurity assistant. Summarize CVE-2010-3763."
out = llm.generate([prompt], SamplingParams(max_tokens=128))[0]
print(out.outputs[0].text)
PY

HF Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Kushalkhemka/CyberOSS-CVE", torch_dtype="bfloat16", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("unsloth/gpt-oss-20b-BF16")

License

Matches upstream unsloth/gpt-oss-20b (LGPL-3.0). Respect dataset terms when redistributing.