Instructions to use inverse-scaling/opt-2.7b_eval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inverse-scaling/opt-2.7b_eval with Transformers:

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

pipe = pipeline("text-generation", model="inverse-scaling/opt-2.7b_eval")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inverse-scaling/opt-2.7b_eval")
model = AutoModelForCausalLM.from_pretrained("inverse-scaling/opt-2.7b_eval", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inverse-scaling/opt-2.7b_eval with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inverse-scaling/opt-2.7b_eval"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inverse-scaling/opt-2.7b_eval",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/inverse-scaling/opt-2.7b_eval

SGLang

How to use inverse-scaling/opt-2.7b_eval 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 "inverse-scaling/opt-2.7b_eval" \
    --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": "inverse-scaling/opt-2.7b_eval",
		"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 "inverse-scaling/opt-2.7b_eval" \
        --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": "inverse-scaling/opt-2.7b_eval",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use inverse-scaling/opt-2.7b_eval with Docker Model Runner:
```
docker model run hf.co/inverse-scaling/opt-2.7b_eval
```

opt-2.7b_eval

Commit History

Jan 2, 2023

13:01
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#19)⁠

MicPie +1: autoevaluator

a2de279

Nov 14, 2022

20:44
Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#18)⁠

MicPie +1: autoevaluator

7efae61
20:43
Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#17)⁠

MicPie +1: autoevaluator

d4491fe
20:43
Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#16)⁠

MicPie +1: autoevaluator

44a34de

Nov 7, 2022

11:40
Add evaluation results on the mathemakitten--winobias_antistereotype_test_cot_v3 config and test split of mathemakitten/winobias_antistereotype_test_cot_v3 (#13)⁠

MicPie +1: autoevaluator

7e07887

Nov 3, 2022

19:58
Add evaluation results on the mathemakitten--winobias_antistereotype_test_cot_v1 config and test split of mathemakitten/winobias_antistereotype_test_cot_v1 (#12)⁠

MicPie +1: autoevaluator

f454423

Oct 9, 2022

18:00
Add evaluation results on the inverse-scaling--hindsight-neglect-10shot config and train split of inverse-scaling/hindsight-neglect-10shot (#6)⁠

MicPie +1: autoevaluator

99c9b7f

Oct 8, 2022

13:15
Update README.md

MicPie

f031bd2
13:14
Update README.md

MicPie

eaa0bb2
13:02
Add evaluation results on the inverse-scaling--NeQA config and train split of inverse-scaling/NeQA (#3)⁠

MicPie +1: autoevaluator

92250f6
12:46
Update README.md

MicPie

bdc8ddd

Oct 7, 2022

17:21
Add evaluation results on the inverse-scaling--41 config and train split of inverse-scaling/41 (#2)⁠

MicPie +1: autoevaluator

7e749b5

Oct 6, 2022

09:11
cp opt-2.7b

Michael Pieler

2a83fcf

Oct 5, 2022

15:09
initial commit

MicPie

83e34fe

Commit History

Jan 2, 2023

Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#19)⁠

Nov 14, 2022

Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#18)⁠

Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#17)⁠

Add evaluation results on the mathemakitten--winobias_antistereotype_test_v5 config and test split of mathemakitten/winobias_antistereotype_test_v5 (#16)⁠

Nov 7, 2022

Add evaluation results on the mathemakitten--winobias_antistereotype_test_cot_v3 config and test split of mathemakitten/winobias_antistereotype_test_cot_v3 (#13)⁠

Nov 3, 2022

Add evaluation results on the mathemakitten--winobias_antistereotype_test_cot_v1 config and test split of mathemakitten/winobias_antistereotype_test_cot_v1 (#12)⁠

Oct 9, 2022

Add evaluation results on the inverse-scaling--hindsight-neglect-10shot config and train split of inverse-scaling/hindsight-neglect-10shot (#6)⁠

Oct 8, 2022

Update README.md

Update README.md

Add evaluation results on the inverse-scaling--NeQA config and train split of inverse-scaling/NeQA (#3)⁠

Update README.md

Oct 7, 2022

Add evaluation results on the inverse-scaling--41 config and train split of inverse-scaling/41 (#2)⁠

Oct 6, 2022

cp opt-2.7b

Oct 5, 2022

initial commit