Instructions to use itsliupeng/llama2_70b_mmlu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itsliupeng/llama2_70b_mmlu with Transformers:

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

pipe = pipeline("text-generation", model="itsliupeng/llama2_70b_mmlu")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("itsliupeng/llama2_70b_mmlu")
model = AutoModelForCausalLM.from_pretrained("itsliupeng/llama2_70b_mmlu")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use itsliupeng/llama2_70b_mmlu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itsliupeng/llama2_70b_mmlu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itsliupeng/llama2_70b_mmlu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/itsliupeng/llama2_70b_mmlu

SGLang

How to use itsliupeng/llama2_70b_mmlu 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 "itsliupeng/llama2_70b_mmlu" \
    --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": "itsliupeng/llama2_70b_mmlu",
		"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 "itsliupeng/llama2_70b_mmlu" \
        --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": "itsliupeng/llama2_70b_mmlu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use itsliupeng/llama2_70b_mmlu with Docker Model Runner:
```
docker model run hf.co/itsliupeng/llama2_70b_mmlu
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

We are utilizing the mmlu_recall dataset to continuously train the Llama-2-70b-hf model, aiming to enhance performance on mmlu metrics, while ensuring that other metric performances remain unaffected.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.24
AI2 Reasoning Challenge (25-Shot)	65.61
HellaSwag (10-Shot)	87.37
MMLU (5-Shot)	71.89
TruthfulQA (0-shot)	49.15
Winogrande (5-shot)	82.40
GSM8k (5-shot)	52.99

Downloads last month: 243

Safetensors

Model size

69B params

Tensor type

BF16

Model tree for itsliupeng/llama2_70b_mmlu

Quantizations

1 model

Dataset used to train itsliupeng/llama2_70b_mmlu

Space using itsliupeng/llama2_70b_mmlu 1

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

65.610
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.370
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

71.890
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

49.150
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.400
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

52.990