Instructions to use iliemihai/gpt-neo-romanian-125m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iliemihai/gpt-neo-romanian-125m with Transformers:

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

pipe = pipeline("text-generation", model="iliemihai/gpt-neo-romanian-125m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iliemihai/gpt-neo-romanian-125m")
model = AutoModelForCausalLM.from_pretrained("iliemihai/gpt-neo-romanian-125m")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iliemihai/gpt-neo-romanian-125m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iliemihai/gpt-neo-romanian-125m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iliemihai/gpt-neo-romanian-125m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iliemihai/gpt-neo-romanian-125m

SGLang

How to use iliemihai/gpt-neo-romanian-125m 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 "iliemihai/gpt-neo-romanian-125m" \
    --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": "iliemihai/gpt-neo-romanian-125m",
		"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 "iliemihai/gpt-neo-romanian-125m" \
        --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": "iliemihai/gpt-neo-romanian-125m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iliemihai/gpt-neo-romanian-125m with Docker Model Runner:
```
docker model run hf.co/iliemihai/gpt-neo-romanian-125m
```

iliemihai commited on Apr 7, 2023

Commit

5b9beb8

1 Parent(s): 96ed2e0

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -0

README.md CHANGED Viewed

@@ -16,6 +16,21 @@ This model is a GPT-Neo transformer decoder model designed using EleutherAI's re
 It was trained on a thoroughly cleaned corpus of Romanian text of about 40GB composed of Oscar, Opus, Wikipedia, literature and various other bits and pieces of text, joined together and deduplicated. It was trained for about a month, totaling 5.8M steps on a v3 TPU machine.
 ### Authors:
 * Dumitrescu Stefan
 * Mihai Ilie

 It was trained on a thoroughly cleaned corpus of Romanian text of about 40GB composed of Oscar, Opus, Wikipedia, literature and various other bits and pieces of text, joined together and deduplicated. It was trained for about a month, totaling 5.8M steps on a v3 TPU machine.
+```python
+from transformers import GPTNeoForCausalLM, GPT2Tokenizer
+model = GPTNeoForCausalLM.from_pretrained("iliemihai/gpt-neo-romanian-125m")
+tokenizer = GPT2Tokenizer.from_pretrained("iliemihai/gpt-neo-romanian-125m")
+prompt = "Cine a fost mihai eminescu"
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+output = model.generate(input_ids, penalty_alpha=0.6, top_k=4, max_length=64)
+result = tokenizer.decode(output[0], skip_special_tokens=True)
+print(result)
+```
 ### Authors:
 * Dumitrescu Stefan
 * Mihai Ilie