Instructions to use pankajmathur/model_420_preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/model_420_preview with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/model_420_preview")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/model_420_preview")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/model_420_preview")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pankajmathur/model_420_preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/model_420_preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/model_420_preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/model_420_preview

SGLang

How to use pankajmathur/model_420_preview 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 "pankajmathur/model_420_preview" \
    --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": "pankajmathur/model_420_preview",
		"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 "pankajmathur/model_420_preview" \
        --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": "pankajmathur/model_420_preview",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/model_420_preview with Docker Model Runner:
```
docker model run hf.co/pankajmathur/model_420_preview
```

LlaMA-2 License, more details coming soon...

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	55.99
ARC (25-shot)	67.06
HellaSwag (10-shot)	87.26
MMLU (5-shot)	69.85
TruthfulQA (0-shot)	44.57
Winogrande (5-shot)	83.35
GSM8K (5-shot)	33.21
DROP (3-shot)	6.6

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	64.22
AI2 Reasoning Challenge (25-Shot)	67.06
HellaSwag (10-Shot)	87.26
MMLU (5-Shot)	69.85
TruthfulQA (0-shot)	44.57
Winogrande (5-shot)	83.35
GSM8k (5-shot)	33.21

Downloads last month: 260

Spaces using pankajmathur/model_420_preview 29

Evaluation results

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

67.060
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.260
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

69.850
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.570
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.350
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

33.210