Instructions to use ducthang1703/cbg-llama2-7b-beta0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ducthang1703/cbg-llama2-7b-beta0 with Transformers:

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

pipe = pipeline("text-generation", model="ducthang1703/cbg-llama2-7b-beta0")
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("ducthang1703/cbg-llama2-7b-beta0")
model = AutoModelForCausalLM.from_pretrained("ducthang1703/cbg-llama2-7b-beta0", 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 ducthang1703/cbg-llama2-7b-beta0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ducthang1703/cbg-llama2-7b-beta0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ducthang1703/cbg-llama2-7b-beta0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ducthang1703/cbg-llama2-7b-beta0

SGLang

How to use ducthang1703/cbg-llama2-7b-beta0 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 "ducthang1703/cbg-llama2-7b-beta0" \
    --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": "ducthang1703/cbg-llama2-7b-beta0",
		"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 "ducthang1703/cbg-llama2-7b-beta0" \
        --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": "ducthang1703/cbg-llama2-7b-beta0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ducthang1703/cbg-llama2-7b-beta0 with Docker Model Runner:
```
docker model run hf.co/ducthang1703/cbg-llama2-7b-beta0
```

cbg-llama2-7b-beta0

Full-parameter CBG v2 defense of meta-llama/Llama-2-7b-chat-hf, trained with src/cbg/train_v2.py on the SEAM main-run data recipe (RepNoise BeaverTails refusals, 4,000 defense rows; Alpaca, 4,000 benign rows).

Prompt format: Question: {prompt}\nAnswer: (no chat template), as in training.

Training settings


steps	500
lr	2e-05
scheduler	cosine
batch m / n	8 / 32
alpha	1.0
beta	0.0
k	4
radius r	1.1e-07
lazy_period	4
lazy_mode	reuse
num_sign_draws	1
geometry_clip_factor	3.0
max length (safety / benign)	256 / 256
weights dtype	bfloat16

Geometry (D_geo)


geo/log_eta_k (step 0)	-0.02352772316966905
geo/log_eta_k (step 500)	-0.02482512454428497
delta log eta_k	-0.0012974013746159183

Provenance


base model	meta-llama/Llama-2-7b-chat-hf @ f5db02db724555f92da89c216ac04704f23d4590
config sha256	000d943023a55fdfc8589476670072caa3c6038f47f716f1c3e476c14527bf71
data manifest sha256	d08a4023a7c11c4a3d01259356569ec19766bb7d754d194841dff60836d7a898
torch	2.5.1+cu124
GPUs	NVIDIA H200 NVL, NVIDIA H200 NVL

Training records (config, identity, per-step log, metrics) are in training/.

License

A derivative of Llama 2, distributed under the Llama 2 Community License Agreement; use is subject to its terms and Acceptable Use Policy.

Downloads last month: 178

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for ducthang1703/cbg-llama2-7b-beta0

Base model

meta-llama/Llama-2-7b-chat-hf

Finetuned

(711)

this model