Instructions to use alokeshproy1964/security-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alokeshproy1964/security-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "alokeshproy1964/security-lora")

Transformers

How to use alokeshproy1964/security-lora with Transformers:

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

pipe = pipeline("text-generation", model="alokeshproy1964/security-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alokeshproy1964/security-lora")
model = AutoModelForCausalLM.from_pretrained("alokeshproy1964/security-lora", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alokeshproy1964/security-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alokeshproy1964/security-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alokeshproy1964/security-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alokeshproy1964/security-lora

SGLang

How to use alokeshproy1964/security-lora 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 "alokeshproy1964/security-lora" \
    --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": "alokeshproy1964/security-lora",
		"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 "alokeshproy1964/security-lora" \
        --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": "alokeshproy1964/security-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alokeshproy1964/security-lora with Docker Model Runner:
```
docker model run hf.co/alokeshproy1964/security-lora
```

See axolotl config

axolotl version: 0.17.0.dev0

base_model: Qwen/Qwen2.5-0.5B-Instruct
load_in_4bit: true
adapter: qlora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.0
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
micro_batch_size: 1
gradient_accumulation_steps: 2
num_epochs: 1
learning_rate: 2e-4
sequence_len: 512
  - path: /workspace/datasets/real_data.jsonl
    type: alpaca
output_dir: /workspace/output/run1
val_set_size: 0.1
eval_strategy: steps
eval_steps: 10

workspace/output/run1

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the /workspace/datasets/real_data.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.0219
Ppl: 1.0222
Memory/max Active (gib): 0.58
Memory/max Allocated (gib): 0.58
Memory/device Reserved (gib): 0.71

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2
training_steps: 45

Training results

Training Loss	Epoch	Step	Validation Loss	Ppl	Active (gib)	Allocated (gib)	Reserved (gib)
No log	0	0	3.6679	39.1691	0.54	0.54	0.96
1.9445	0.2222	10	1.1011	3.0074	0.58	0.58	0.71
0.0700	0.4444	20	0.1646	1.1790	0.58	0.58	0.71
0.0087	0.6667	30	0.0791	1.0823	0.58	0.58	0.71
0.0062	0.8889	40	0.0411	1.0420	0.58	0.58	0.71
0.0386	1.0	45	0.0219	1.0222	0.58	0.58	0.71

Framework versions

PEFT 0.19.1
Transformers 5.10.2
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: 29

Model tree for alokeshproy1964/security-lora

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Adapter

(864)

this model