Instructions to use exploitintel/cve-cwe-qwen3-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use exploitintel/cve-cwe-qwen3-32b with Transformers:

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

pipe = pipeline("text-generation", model="exploitintel/cve-cwe-qwen3-32b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("exploitintel/cve-cwe-qwen3-32b")
model = AutoModelForCausalLM.from_pretrained("exploitintel/cve-cwe-qwen3-32b")
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]:]))

llama-cpp-python

How to use exploitintel/cve-cwe-qwen3-32b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="exploitintel/cve-cwe-qwen3-32b",
	filename="q32-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use exploitintel/cve-cwe-qwen3-32b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Use Docker

docker model run hf.co/exploitintel/cve-cwe-qwen3-32b:Q4_K_M

LM Studio
Jan

vLLM

How to use exploitintel/cve-cwe-qwen3-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "exploitintel/cve-cwe-qwen3-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "exploitintel/cve-cwe-qwen3-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/exploitintel/cve-cwe-qwen3-32b:Q4_K_M

SGLang

How to use exploitintel/cve-cwe-qwen3-32b 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 "exploitintel/cve-cwe-qwen3-32b" \
    --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": "exploitintel/cve-cwe-qwen3-32b",
		"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 "exploitintel/cve-cwe-qwen3-32b" \
        --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": "exploitintel/cve-cwe-qwen3-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use exploitintel/cve-cwe-qwen3-32b with Ollama:
```
ollama run hf.co/exploitintel/cve-cwe-qwen3-32b:Q4_K_M
```

Unsloth Studio

How to use exploitintel/cve-cwe-qwen3-32b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for exploitintel/cve-cwe-qwen3-32b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for exploitintel/cve-cwe-qwen3-32b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for exploitintel/cve-cwe-qwen3-32b to start chatting

How to use exploitintel/cve-cwe-qwen3-32b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "exploitintel/cve-cwe-qwen3-32b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use exploitintel/cve-cwe-qwen3-32b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use exploitintel/cve-cwe-qwen3-32b with Docker Model Runner:
```
docker model run hf.co/exploitintel/cve-cwe-qwen3-32b:Q4_K_M
```

Lemonade

How to use exploitintel/cve-cwe-qwen3-32b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull exploitintel/cve-cwe-qwen3-32b:Q4_K_M

Run and chat with the model

lemonade run user.cve-cwe-qwen3-32b-Q4_K_M

List all available models

lemonade list

cve-cwe-qwen3-32b / README.md

exploitintel

Note: ollama run line unverified end-to-end; use explicit Modelfile TEMPLATE if output rambles

89faccd verified 4 days ago

preview code

raw

history blame contribute delete

5.33 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-32B
	datasets:
	- exploitintel/cve-cwe-consensus
	language:
	- en
	tags:
	- cybersecurity
	- vulnerability
	- cve
	- cwe
	- text-classification
	- qlora
	- unsloth
	pipeline_tag: text-generation
	library_name: transformers
	---

	# CVE → CWE Classifier (Qwen3-32B)

	A QLoRA fine-tune of Qwen3-32B that maps a free-text CVE description to the **CWE weakness
	ID(s)** it corresponds to. The LoRA adapter is merged into the base and released in 16-bit, so it
	loads directly with `transformers`. A smaller/faster variant is available at
	[`exploitintel/cve-cwe-qwen3-8b`](https://huggingface.co/exploitintel/cve-cwe-qwen3-8b).

	Trained only on labels where NVD and the CNA agree after roll-up to CWE View-1003 — see the
	[`cve-cwe-consensus`](https://huggingface.co/datasets/exploitintel/cve-cwe-consensus) dataset.

	## Results (held-out test split, 6,802 rows)

	\| Metric \| This model (32B) \| 8B variant \|
	\|---\|---\|---\|
	\| Exact-match \| 0.707 \| 0.676 \|
	\| Micro-F1 \| 0.729 \| 0.702 \|
	\| Macro-F1 \| 0.595 \| 0.511 \|

	By difficulty (does the description name the weakness, or must it be inferred?):

	\| Stratum \| n \| Exact-match \| Micro-F1 \|
	\|---\|---\|---\|---\|
	\| Easy (weakness named) \| 2,046 \| 0.871 \| 0.893 \|
	\| Hard (must infer) \| 4,756 \| 0.636 \| 0.657 \|

	Both models are scored identically; the 32B's gains are largest on macro-F1 (rare/long-tail CWEs)
	and the hard inference split.

	Reading the numbers:
	- Macro-F1 is over the union of gold and predicted labels (118 = 117 gold + ~1 the model predicted
	outside the gold set), so 0.595 is a conservative figure. The low out-of-label count also means
	the model rarely hallucinates non-existent CWEs.
	- Exact-match has an inherent ceiling of ~98.3%: ~1.74% of the test set (273 groups / 1,205 rows)
	are identical descriptions mapped to different CWEs (e.g. a bare "Windows Kernel Elevation of
	Privilege Vulnerability"), which a description-only model cannot disambiguate.
	- Scores are on the capped/balanced test split (~30% "easy" rows), so they are not directly
	comparable to metrics measured on a different (e.g. natural-distribution) split.

	## Usage

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	mid = "exploitintel/cve-cwe-qwen3-32b"
	tok = AutoTokenizer.from_pretrained(mid)
	model = AutoModelForCausalLM.from_pretrained(mid, torch_dtype="auto", device_map="auto")

	messages = [
	{"role": "system", "content": "You are a vulnerability analyst. Given a CVE description, "
	"reply with only the CWE ID(s) it maps to, comma-separated."},
	{"role": "user", "content": "A SQL injection vulnerability in the login endpoint allows an "
	"unauthenticated attacker to execute arbitrary SQL via the username parameter."},
	]
	inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
	out = model.generate(inputs, max_new_tokens=32, do_sample=False)
	print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
	# -> CWE-89
	```

	### GGUF / Ollama

	A `Q4_K_M` GGUF (~20 GB) is included in this repo for local runners — needs ~24 GB VRAM:

	```bash
	ollama run hf.co/exploitintel/cve-cwe-qwen3-32b:Q4_K_M
	```

	Set the same system prompt (`/set system You are a vulnerability analyst...`) so it returns bare CWE IDs.

	> Note: This Ollama command has not been verified end-to-end. This is a standard `qwen3`
	> model so the embedded template should apply normally — but if `ollama run` ignores the
	> system prompt and produces rambling text instead of a bare CWE ID, supply an explicit
	> ChatML Modelfile `TEMPLATE` as shown in the [Qwen3.5-4B card](https://huggingface.co/exploitintel/cve-cwe-qwen35-4b).

	## Training

	- Base: `Qwen/Qwen3-32B` (trained 4-bit via `unsloth/Qwen3-32B-unsloth-bnb-4bit`)
	- Method: QLoRA (4-bit) with Unsloth, merged to 16-bit · released checkpoint: checkpoint-960 (final; eval loss declined monotonically through training)
	- Dataset: [`exploitintel/cve-cwe-consensus`](https://huggingface.co/datasets/exploitintel/cve-cwe-consensus) — 69,386 rows (55,810 / 6,774 / 6,802), majority CWEs capped at 2,500
	- Settings: 2 epochs · context 512 · LR 2e-4 · AdamW 8-bit · linear schedule · packing on · train-on-completions-only off · seed 3407
	- LoRA fine-tune, rank 16 (confirmed); adapter merged into the base. Exact LoRA alpha, batch size, and weight decay were not logged to the repo.

	## Prompt format

	ChatML (Qwen3 standard). Fixed system prompt; the description is the only user input.

	- system: `You are a vulnerability analyst. Given a CVE description, reply with only the CWE ID(s) it maps to, comma-separated.`
	- user: the CVE description
	- assistant: `CWE-79, CWE-80`

	## Limitations

	- CWEs below the dataset's 50-example floor are not in the label space and won't be predicted.
	- Outputs CWE IDs as text; validate against the official CWE list.
	- English-only; descriptions only (no code, CVSS, or references).
	- A triage/assist aid, not an authoritative CWE assignment — human-review before acting.

	## License

	Apache-2.0 (inherited from Qwen3-32B). Dataset derives from public upstreams (NVD, MITRE CVE/CWE).