Instructions to use ramitha2002/SecFix-CVE-Remediation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramitha2002/SecFix-CVE-Remediation with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("fdtn-ai/Foundation-Sec-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "ramitha2002/SecFix-CVE-Remediation")

Transformers

How to use ramitha2002/SecFix-CVE-Remediation with Transformers:

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

pipe = pipeline("text-generation", model="ramitha2002/SecFix-CVE-Remediation")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ramitha2002/SecFix-CVE-Remediation", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ramitha2002/SecFix-CVE-Remediation with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ramitha2002/SecFix-CVE-Remediation"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ramitha2002/SecFix-CVE-Remediation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ramitha2002/SecFix-CVE-Remediation

SGLang

How to use ramitha2002/SecFix-CVE-Remediation 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 "ramitha2002/SecFix-CVE-Remediation" \
    --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": "ramitha2002/SecFix-CVE-Remediation",
		"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 "ramitha2002/SecFix-CVE-Remediation" \
        --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": "ramitha2002/SecFix-CVE-Remediation",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ramitha2002/SecFix-CVE-Remediation with Docker Model Runner:
```
docker model run hf.co/ramitha2002/SecFix-CVE-Remediation
```

SecFix-CVE-Remediation / epoch_01_metrics.json

ramitha2002

Upload SecFix LoRA adapter

b5d5dbd verified 15 days ago

Raw

History Blame Contribute Delete

964 Bytes

	{
	"best_metric": 0.0016579071525484324,
	"best_model_checkpoint": "/root/i/j/server/outputs/checkpoints/secfix_server_lora/checkpoint-6250",
	"epoch": 1.0,
	"epoch_number": 1,
	"global_step": 6250,
	"logs": [
	{
	"epoch": 0.992,
	"grad_norm": 0.0026881410740315914,
	"learning_rate": 3.4926330210360846e-09,
	"loss": 0.016918934881687164,
	"step": 6200
	},
	{
	"epoch": 0.9952,
	"grad_norm": 0.0003010830550920218,
	"learning_rate": 1.2904819436210247e-09,
	"loss": 4.504423122853041e-05,
	"step": 6220
	},
	{
	"epoch": 0.9984,
	"grad_norm": 0.002738719340413809,
	"learning_rate": 1.6248829433518355e-10,
	"loss": 0.000680431816726923,
	"step": 6240
	},
	{
	"epoch": 1.0,
	"eval_loss": 0.0016579071525484324,
	"eval_runtime": 251.4825,
	"eval_samples_per_second": 39.764,
	"eval_steps_per_second": 9.941,
	"step": 6250
	}
	]
	}