Instructions to use L33tcode/llama-3-8b-CEH-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use L33tcode/llama-3-8b-CEH-hf with Transformers:

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

pipe = pipeline("text-generation", model="L33tcode/llama-3-8b-CEH-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("L33tcode/llama-3-8b-CEH-hf")
model = AutoModelForCausalLM.from_pretrained("L33tcode/llama-3-8b-CEH-hf", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use L33tcode/llama-3-8b-CEH-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "L33tcode/llama-3-8b-CEH-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "L33tcode/llama-3-8b-CEH-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/L33tcode/llama-3-8b-CEH-hf

SGLang

How to use L33tcode/llama-3-8b-CEH-hf 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 "L33tcode/llama-3-8b-CEH-hf" \
    --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": "L33tcode/llama-3-8b-CEH-hf",
		"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 "L33tcode/llama-3-8b-CEH-hf" \
        --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": "L33tcode/llama-3-8b-CEH-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use L33tcode/llama-3-8b-CEH-hf 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 L33tcode/llama-3-8b-CEH-hf 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 L33tcode/llama-3-8b-CEH-hf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for L33tcode/llama-3-8b-CEH-hf to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="L33tcode/llama-3-8b-CEH-hf",
    max_seq_length=2048,
)

Docker Model Runner
How to use L33tcode/llama-3-8b-CEH-hf with Docker Model Runner:
```
docker model run hf.co/L33tcode/llama-3-8b-CEH-hf
```

L33tcode commited on May 29, 2024

Commit

cfaf35f

verified ·

1 Parent(s): a9c5c3d

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ tags:
 base_model: cognitivecomputations/dolphin-2.9-llama3-8b
 ---
-# Model Card for LLama3-CyberSec
 ## Model Details
@@ -23,11 +23,11 @@ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
 ## Model Description
-LLama3-CyberSec is a fine-tuned version of the LLama3 language model, adapted specifically for cybersecurity applications. Utilizing Unsloth and Huggingface's TRL library, this model was trained 2x faster to effectively handle tasks related to identifying vulnerabilities, analyzing security protocols, and understanding complex cybersecurity concepts.
 ## Intended Use
-LLama3-CyberSec is designed for cybersecurity professionals and researchers to:
 - Identify and analyze potential security vulnerabilities.
 - Understand and implement various cybersecurity methodologies.
@@ -53,7 +53,7 @@ This model is uncensored, meaning it can generate content that might be consider
 ## Future Work
-Future versions of LLama3-CyberSec may include:
 - Enhanced filtering to prevent the generation of unethical or harmful content.
 - Additional training data covering more cybersecurity aspects.
@@ -61,8 +61,8 @@ Future versions of LLama3-CyberSec may include:
 ## Disclaimer
-LLama3-CyberSec is provided "as is" without any warranties or guarantees. Use this model at your own risk and comply with all applicable laws and regulations. The developers disclaim any liability for damage or harm resulting from its use.
-By using LLama3-CyberSec, you agree to these terms and commit to using the model responsibly and ethically.
 For more information on responsible use and best practices in cybersecurity, please refer to [insert relevant guidelines or resources].

 base_model: cognitivecomputations/dolphin-2.9-llama3-8b
 ---
+# Model Card for (llama-3-CEH) LLama3-CyberSec
 ## Model Details
 ## Model Description
+(llama-3-CEH) LLama3-CyberSec is a fine-tuned version of the LLama3 language model, adapted specifically for cybersecurity applications. Utilizing Unsloth and Huggingface's TRL library, this model was trained 2x faster to effectively handle tasks related to identifying vulnerabilities, analyzing security protocols, and understanding complex cybersecurity concepts.
 ## Intended Use
+(llama-3-CEH) LLama3-CyberSec is designed for cybersecurity professionals and researchers to:
 - Identify and analyze potential security vulnerabilities.
 - Understand and implement various cybersecurity methodologies.
 ## Future Work
+Future versions of (llama-3-CEH) LLama3-CyberSec may include:
 - Enhanced filtering to prevent the generation of unethical or harmful content.
 - Additional training data covering more cybersecurity aspects.
 ## Disclaimer
+(llama-3-CEH) LLama3-CyberSec is provided "as is" without any warranties or guarantees. Use this model at your own risk and comply with all applicable laws and regulations. The developers disclaim any liability for damage or harm resulting from its use.
+By using (llama-3-CEH) LLama3-CyberSec, you agree to these terms and commit to using the model responsibly and ethically.
 For more information on responsible use and best practices in cybersecurity, please refer to [insert relevant guidelines or resources].