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

Libraries

How to use EleutherAI/pythia-160m with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/pythia-160m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/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": "EleutherAI/pythia-160m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/pythia-160m

SGLang

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

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

pythia-160m

Commit History

Jun 12, 2023

21:46
Adding `safetensors` variant of this model⁠

SFconvertbot

cf81a57

Jun 8, 2023

10:14
fix batch size and add paper

avi-skowron

26b94a3

Apr 3, 2023

18:39
Upload pytorch_model.bin

hails

57c4cbf
18:39
Upload tokenizer.json

hails

40f6318
18:39
Upload tokenizer_config.json

hails

4560d92
18:39
Upload config.json

hails

521f765
18:39
Upload special_tokens_map.json

hails

7e30bb8

Mar 29, 2023

22:32
create updated readme

avi-skowron

64a5b91

Mar 23, 2023

13:46
Upload config.json

hails

e0a0251
13:46
Upload special_tokens_map.json

hails

5c39738
13:46
Upload tokenizer.json

hails

4c6801b
13:46
Upload pytorch_model.bin

hails

0243faf
13:45
Upload tokenizer_config.json

hails

a2e7dc4

Mar 22, 2023

16:41
Upload config.json

hails

610be53
16:41
Upload pytorch_model.bin

hails

ac17eb6
16:41
Upload special_tokens_map.json

hails

a6b1312
16:41
Upload tokenizer_config.json

hails

30ac103
16:41
Upload tokenizer.json

hails

e1fd0cf
16:34
Upload special_tokens_map.json

hails

1dc1688
16:34
Upload config.json

hails

cd86582
16:34
Upload tokenizer_config.json

hails

a82aaf0
16:34
Upload tokenizer.json

hails

d38718f
16:34
Upload pytorch_model.bin

hails

4fb48c3
16:31
Upload config.json

hails

6e10859
16:31
Upload tokenizer_config.json

hails

5e3f0aa
16:31
Upload pytorch_model.bin

hails

e4d63e7
16:31
Upload special_tokens_map.json

hails

4550161
16:31
Upload tokenizer.json

hails

f96ca98
16:30
Upload config.json

hails

7acef1e
16:30
Upload special_tokens_map.json

hails

2be6e37
16:30
Upload tokenizer.json

hails

9cbd7c8
16:30
Upload tokenizer_config.json

hails

b83afbb
16:30
Upload pytorch_model.bin

hails

f59fbc6
16:29
Upload pytorch_model.bin

hails

85aa9e2
16:29
Upload tokenizer_config.json

hails

9cab9b4
16:29
Upload tokenizer.json

hails

04db95c
16:29
Upload special_tokens_map.json

hails

5f8e072
16:29
Upload config.json

hails

575bf7c
16:20
Upload tokenizer_config.json

hails

84b79d4
16:20
Upload tokenizer.json

hails

26b13cc
16:20
Upload special_tokens_map.json

hails

fd70af8
16:20
Upload config.json

hails

be61115

Feb 8, 2023

19:25
initial commit

Hailey Schoelkopf

8746001

Commit History

Jun 12, 2023

Adding `safetensors` variant of this model⁠

Jun 8, 2023

fix batch size and add paper

Apr 3, 2023

Upload pytorch_model.bin

Upload tokenizer.json

Upload tokenizer_config.json

Upload config.json

Upload special_tokens_map.json

Mar 29, 2023

create updated readme

Mar 23, 2023

Upload config.json

Upload special_tokens_map.json

Upload tokenizer.json

Upload pytorch_model.bin

Upload tokenizer_config.json

Mar 22, 2023

Upload config.json

Upload pytorch_model.bin

Upload special_tokens_map.json

Upload tokenizer_config.json

Upload tokenizer.json

Upload special_tokens_map.json

Upload config.json

Upload tokenizer_config.json

Upload tokenizer.json

Upload pytorch_model.bin

Upload config.json

Upload tokenizer_config.json

Upload pytorch_model.bin

Upload special_tokens_map.json

Upload tokenizer.json

Upload config.json

Upload special_tokens_map.json

Upload tokenizer.json

Upload tokenizer_config.json

Upload pytorch_model.bin

Upload pytorch_model.bin

Upload tokenizer_config.json

Upload tokenizer.json

Upload special_tokens_map.json

Upload config.json

Upload tokenizer_config.json

Upload tokenizer.json

Upload special_tokens_map.json

Upload config.json

Feb 8, 2023

initial commit