Instructions to use wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new with Transformers:

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

pipe = pipeline("text-generation", model="wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new")
model = AutoModelForCausalLM.from_pretrained("wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new", 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 wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new

SGLang

How to use wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new 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 "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new" \
    --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": "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new",
		"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 "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new" \
        --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": "wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new with Docker Model Runner:
```
docker model run hf.co/wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new
```

Llama-2-7B SSFT-CB + ARC-Challenge AsFT

This is the fully merged checkpoint obtained by AsFT fine-tuning wvnvwn/llama2-7b-chat-lr5e-5-ssft-cb on the ARC-Challenge training split.

Training used 1,119 examples for 3 epochs with learning rate 3e-4, physical and effective batch size 16, cosine scheduling with warmup ratio 0.1, BF16, maximum sequence length 1,024, and seed 42. The LoRA configuration used rank 16, alpha 32, dropout 0.05, and target modules q_proj, k_proj, v_proj, up_proj, and down_proj. AsFT used 160 alignment directions and lambda_reg=1.0.

The Llama-2 chat template was applied and prompt tokens were masked from the training loss. The saved weights have already been merged into the starting model; no separate adapter is required for inference.

Downloads last month: 13

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for wvnvwn/llama2-7b-chat-lr5e-5-arcc-lr3e-4-cbasft-new-new

Base model

wvnvwn/llama2-7b-chat-lr5e-5-ssft-cb

Finetuned

(6)

this model