Instructions to use afterless/reverse-pythia-160m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afterless/reverse-pythia-160m with Transformers:

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

pipe = pipeline("text-generation", model="afterless/reverse-pythia-160m")

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

tokenizer = AutoTokenizer.from_pretrained("afterless/reverse-pythia-160m")
model = AutoModelForCausalLM.from_pretrained("afterless/reverse-pythia-160m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use afterless/reverse-pythia-160m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afterless/reverse-pythia-160m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afterless/reverse-pythia-160m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afterless/reverse-pythia-160m

SGLang

How to use afterless/reverse-pythia-160m 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 "afterless/reverse-pythia-160m" \
    --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": "afterless/reverse-pythia-160m",
		"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 "afterless/reverse-pythia-160m" \
        --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": "afterless/reverse-pythia-160m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use afterless/reverse-pythia-160m with Docker Model Runner:
```
docker model run hf.co/afterless/reverse-pythia-160m
```

reverse-pythia-160m

Commit History

Aug 11, 2023

15:00
Adding `safetensors` variant of this model⁠

SFconvertbot

7db280f
02:29
Upload special_tokens_map.json

afterless

90711a5
02:29
Upload tokenizer_config.json

afterless

f028e3c
02:29
Upload generation_config.json

afterless

57d0129
02:29
Upload config.json

afterless

11932af
02:29
Upload tokenizer.json

afterless

bfcb58e
02:29
Upload pytorch_model.bin

afterless

413c864

Aug 2, 2023

21:39
Delete pytorch_model_72000.bin

afterless

7445d78
21:38
Update README.md

afterless

832c182
21:37
Update README.md

afterless

0ffb679
21:34
Create README.md

afterless

017d6eb
21:33
Upload special_tokens_map.json

afterless

3f166a7
21:33
Upload tokenizer_config.json

afterless

26bebf5
21:33
Upload config.json

afterless

48186a7
21:33
Upload tokenizer.json

afterless

86eb792
21:33
Upload pytorch_model.bin

afterless

e310341
21:30
Upload special_tokens_map.json

afterless

b56e042
21:30
Upload tokenizer_config.json

afterless

7d37be1
21:30
Upload config.json

afterless

4be462a
21:30
Upload tokenizer.json

afterless

3f8cde3
21:30
Upload pytorch_model_72000.bin

afterless

79e7f45
21:29
Upload special_tokens_map.json

afterless

d6935dc
21:29
Upload tokenizer_config.json

afterless

d152740
21:29
Upload tokenizer.json

afterless

54871d4
21:29
Upload pytorch_model_72000.bin

afterless

0addf06
21:25
initial commit

??

b18553c

Commit History

Aug 11, 2023

Adding `safetensors` variant of this model⁠

Upload special_tokens_map.json

Upload tokenizer_config.json

Upload generation_config.json

Upload config.json

Upload tokenizer.json

Upload pytorch_model.bin

Aug 2, 2023

Delete pytorch_model_72000.bin

Update README.md

Update README.md

Create README.md

Upload special_tokens_map.json

Upload tokenizer_config.json

Upload config.json

Upload tokenizer.json

Upload pytorch_model.bin

Upload special_tokens_map.json

Upload tokenizer_config.json

Upload config.json

Upload tokenizer.json

Upload pytorch_model_72000.bin

Upload special_tokens_map.json

Upload tokenizer_config.json

Upload tokenizer.json

Upload pytorch_model_72000.bin

initial commit