Instructions to use heegyu/WizardVicuna-open-llama-3b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heegyu/WizardVicuna-open-llama-3b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="heegyu/WizardVicuna-open-llama-3b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")
model = AutoModelForCausalLM.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use heegyu/WizardVicuna-open-llama-3b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heegyu/WizardVicuna-open-llama-3b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heegyu/WizardVicuna-open-llama-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/heegyu/WizardVicuna-open-llama-3b-v2

SGLang

How to use heegyu/WizardVicuna-open-llama-3b-v2 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 "heegyu/WizardVicuna-open-llama-3b-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heegyu/WizardVicuna-open-llama-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "heegyu/WizardVicuna-open-llama-3b-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heegyu/WizardVicuna-open-llama-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use heegyu/WizardVicuna-open-llama-3b-v2 with Docker Model Runner:
```
docker model run hf.co/heegyu/WizardVicuna-open-llama-3b-v2
```

WizardVicuna-open-llama-3b-v2 / README.md

leaderboard-pr-bot

Adding Evaluation Results

984c374 almost 3 years ago

1.65 kB

datasets:
  - heegyu/wizard_vicuna_70k_v2
license: apache-2.0

Hyperparameters

3/8 epoch(3rd epoch checkpoing while 8epoch training)
1e-4 -> 1e-5 with cosine lr decay
batch size 128
max sequence length 2048
AdamW(weigth decay=0.01, b1=0.9, b2=0.99, grad_clip=1.0)
no warmup
BF16
Base Model: openlm-research/open_llama_3b_v2

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")
model = AutoModelForCausalLM.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")

inputs = tokenizer(["Human: Hi, nice to meet you!\n\nAssistant: "], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=16)
print(tokenizer.batch_decode(outputs, skip_special_tokens=False))

output: ['Human: Hi, nice to meet you!\n\nAssistant: Hello. Great to meet you too. Well, how can I assist you today?<|endoftext|>']

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	34.11
ARC (25-shot)	37.71
HellaSwag (10-shot)	66.6
MMLU (5-shot)	27.23
TruthfulQA (0-shot)	36.8
Winogrande (5-shot)	63.3
GSM8K (5-shot)	0.99
DROP (3-shot)	6.12