Instructions to use Norod78/hebrew_lyrics-gemma2_2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norod78/hebrew_lyrics-gemma2_2b with Transformers:

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

pipe = pipeline("text-generation", model="Norod78/hebrew_lyrics-gemma2_2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norod78/hebrew_lyrics-gemma2_2b")
model = AutoModelForCausalLM.from_pretrained("Norod78/hebrew_lyrics-gemma2_2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norod78/hebrew_lyrics-gemma2_2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Norod78/hebrew_lyrics-gemma2_2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norod78/hebrew_lyrics-gemma2_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Norod78/hebrew_lyrics-gemma2_2b

SGLang

How to use Norod78/hebrew_lyrics-gemma2_2b 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_lyrics-gemma2_2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norod78/hebrew_lyrics-gemma2_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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_lyrics-gemma2_2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Norod78/hebrew_lyrics-gemma2_2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Norod78/hebrew_lyrics-gemma2_2b with Docker Model Runner:
```
docker model run hf.co/Norod78/hebrew_lyrics-gemma2_2b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

מחולל שירים מטופשים :)

from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers import TextStreamer
import torch


model_id = "Norod78/hebrew_lyrics-gemma2_2b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

print(f"model.device = {model.device}")
input_text = "כתוב לי שיר על תפוח אדמה עם חרדה חברתית"

input_template = tokenizer.apply_chat_template([{"role": "user", "content": input_text}], tokenize=False, add_generation_prompt=True)
input_ids = tokenizer(input_template, return_tensors="pt").to(model.device)
outputs = model.generate(**input_ids, max_new_tokens=256, repetition_penalty=1.05, temperature=0.5, no_repeat_ngram_size = 4, do_sample = True)
decoded_output = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
result = decoded_output.replace("user\n", "משתמש:\n").replace("model\n", "\nמודל:\n")
print("result = ", result)


chat = [
  {"role": "user", "content": input_text},
  {"role": "asistant"}
]
chat_with_template = tokenizer.apply_chat_template(chat, tokenize=False)
inputs = tokenizer(
[
    chat_with_template
], return_tensors = "pt").to(model.device)


text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens=256 , repetition_penalty=1.1, temperature=0.6, top_p=0.4, top_k=40, do_sample = True)

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Norod78/hebrew_lyrics-gemma2_2b

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Finetuned

(944)

this model

Quantizations

1 model

Norod78
/

hebrew_lyrics-gemma2_2b

מחולל שירים מטופשים :)

Model tree for Norod78/hebrew_lyrics-gemma2_2b

Datasets used to train Norod78/hebrew_lyrics-gemma2_2b