Instructions to use nouamanetazi/hf-ar-134000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nouamanetazi/hf-ar-134000 with Transformers:

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

pipe = pipeline("text-generation", model="nouamanetazi/hf-ar-134000")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nouamanetazi/hf-ar-134000")
model = AutoModelForCausalLM.from_pretrained("nouamanetazi/hf-ar-134000")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nouamanetazi/hf-ar-134000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nouamanetazi/hf-ar-134000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nouamanetazi/hf-ar-134000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nouamanetazi/hf-ar-134000

SGLang

How to use nouamanetazi/hf-ar-134000 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 "nouamanetazi/hf-ar-134000" \
    --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": "nouamanetazi/hf-ar-134000",
		"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 "nouamanetazi/hf-ar-134000" \
        --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": "nouamanetazi/hf-ar-134000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nouamanetazi/hf-ar-134000 with Docker Model Runner:
```
docker model run hf.co/nouamanetazi/hf-ar-134000
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

1p46G-gemma-fp-dedup-rehydr-ar-350BT-seed-6/transformers/134000

Tokenizer: google/gemma-7b

from transformers import AutoTokenizer, AutoModelForCausalLM
# Initialize model and tokenizer
TEST_PROMPT = "الزرادشتية هي ديانة انتشرت في بلاد"
save_path = "nouamanetazi/hf-ar-134000"
tokenizer = AutoTokenizer.from_pretrained(save_path)
input_ids = tokenizer(TEST_PROMPT, return_tensors="pt")["input_ids"].cuda() # google/gemma-7b
print("Input prompt:", tokenizer.batch_decode(input_ids)[0])

model = AutoModelForCausalLM.from_pretrained(save_path, device="cuda", dtype=torch.bfloat16)
outputs = model.generate(input_ids, max_new_tokens=100)
print("Generated text:", tokenizer.batch_decode(outputs)[0])

Downloads last month: 2

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for nouamanetazi/hf-ar-134000

Finetunes

1 model

Quantizations

1 model