Instructions to use Norod78/hebrew-gpt_neo-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norod78/hebrew-gpt_neo-small with Transformers:

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

pipe = pipeline("text-generation", model="Norod78/hebrew-gpt_neo-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norod78/hebrew-gpt_neo-small")
model = AutoModelForCausalLM.from_pretrained("Norod78/hebrew-gpt_neo-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norod78/hebrew-gpt_neo-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Norod78/hebrew-gpt_neo-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norod78/hebrew-gpt_neo-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Norod78/hebrew-gpt_neo-small

SGLang

How to use Norod78/hebrew-gpt_neo-small 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 "Norod78/hebrew-gpt_neo-small" \
    --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": "Norod78/hebrew-gpt_neo-small",
		"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 "Norod78/hebrew-gpt_neo-small" \
        --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": "Norod78/hebrew-gpt_neo-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Norod78/hebrew-gpt_neo-small with Docker Model Runner:
```
docker model run hf.co/Norod78/hebrew-gpt_neo-small
```

hebrew-gpt_neo-small

Commit History

Adding `safetensors` variant of this model (#1)

d9ee75e

Norod78 commited on Nov 10, 2022

Quant, CPU optimized onnx

fd89195

Doron Adler commited on Aug 14, 2022

Remove 2 fields

12ac2ca

Doron Adler commited on Jul 4, 2022

Move tokenizer.json to non LFS storage

e08d1e3

Doron Adler commited on Jul 4, 2022

Added onnx model

db16f0e

Doron Adler commited on Jul 4, 2022

Update special_tokens_map.json

d0e1863

Norod78 commited on Jul 4, 2022

CC100-Hebrew Dataset

16724d6

Doron Adler commited on Jul 18, 2021

model.ckpt-572300

71dc86b

Doron Adler commited on Jul 18, 2021

"pad_token_id": 50256

f470dc2

Doron Adler commited on Jul 18, 2021

Added FlaxGPTNeoForCausalLM format

97042e4

Doron Adler commited on Jul 14, 2021

model.ckpt-513400

c4eb814

Doron Adler commited on Jul 5, 2021

Update README.md

675cf6d

Norod78 commited on May 13, 2021

Updated model card

8bd28ce

Doron Adler commited on May 13, 2021

Checkpoint 328400

c753749

Doron Adler commited on May 13, 2021

Checkpoint 255800

b0b147d

Doron Adler commited on May 10, 2021

Delete .MD

d12fe91

Doron Adler commited on May 2, 2021

Updated README.md

63ed48d

Norod78 commited on May 2, 2021

Checkpoint 175800

28d7c2d

Doron Adler commited on May 2, 2021

Update model card

08a76ee

Doron Adler commited on May 2, 2021

Create README.md

4d0c4ed

Norod78 commited on May 2, 2021

Added Model Card

d21ef97

Doron Adler commited on May 2, 2021

Checkpoint 105500

cec3667

Norod78 commited on Apr 29, 2021

Hebrew gpt_neo small model ckpt-80500 commit from $USER

d6e6407

Norod78 commited on Apr 28, 2021

initial commit

574871e

system HF Staff commited on Apr 28, 2021

Commit History

Adding `safetensors` variant of this model (#1) d9ee75e

Quant, CPU optimized onnx fd89195

Remove 2 fields 12ac2ca

Move tokenizer.json to non LFS storage e08d1e3

Added onnx model db16f0e

Update special_tokens_map.json d0e1863

CC100-Hebrew Dataset 16724d6

model.ckpt-572300 71dc86b

"pad_token_id": 50256 f470dc2

Added FlaxGPTNeoForCausalLM format 97042e4

model.ckpt-513400 c4eb814

Update README.md 675cf6d

Updated model card 8bd28ce

Checkpoint 328400 c753749

Checkpoint 255800 b0b147d

Delete .MD d12fe91

Updated README.md 63ed48d

Checkpoint 175800 28d7c2d

Update model card 08a76ee

Create README.md 4d0c4ed

Added Model Card d21ef97

Checkpoint 105500 cec3667

Hebrew gpt_neo small model ckpt-80500 commit from $USER d6e6407

initial commit 574871e

Adding `safetensors` variant of this model (#1)

d9ee75e

Quant, CPU optimized onnx

fd89195

Remove 2 fields

12ac2ca

Move tokenizer.json to non LFS storage

e08d1e3

Added onnx model

db16f0e

Update special_tokens_map.json

d0e1863

CC100-Hebrew Dataset

16724d6

model.ckpt-572300

71dc86b

"pad_token_id": 50256

f470dc2

Added FlaxGPTNeoForCausalLM format

97042e4

model.ckpt-513400

c4eb814

Update README.md

675cf6d

Updated model card

8bd28ce

Checkpoint 328400

c753749

Checkpoint 255800

b0b147d

Delete .MD

d12fe91

Updated README.md

63ed48d

Checkpoint 175800

28d7c2d

Update model card

08a76ee

Create README.md

4d0c4ed

Added Model Card

d21ef97

Checkpoint 105500

cec3667

Hebrew gpt_neo small model ckpt-80500 commit from $USER

d6e6407

initial commit

574871e