Instructions to use Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT with Transformers:

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

pipe = pipeline("text-generation", model="Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT")
model = AutoModelForCausalLM.from_pretrained("Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT

SGLang

How to use Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT 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 "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT" \
    --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": "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT",
		"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 "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT" \
        --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": "Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT with Docker Model Runner:
```
docker model run hf.co/Omartificial-Intelligence-Space/Arabic-llama3.1-16bit-FT
```

Omartificial-Intelligence-Space commited on Aug 1, 2024

Commit

ccecc3d

verified ·

1 Parent(s): 165c921

update readme.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,13 +18,13 @@ This fine-tuned model is based on the newly released LLaMA 3.1 model and has bee
 ## Model Summary
-- **Model Type:** Llama3.1 Lora Model
 - **Language(s):** Arabic
 - **Base Model:** [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)
 ## Model Details
-- The model was fine-tuned in 4-bit precision using [unsloth](https://github.com/unslothai/unsloth) for 16k Step on 1 GPU
 ## I prepared for you a Gradio App to do inference with the model and compare its results with the base llama3.1 model

 ## Model Summary
+- **Model Type:** Llama3.1 16 bit Model
 - **Language(s):** Arabic
 - **Base Model:** [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)
 ## Model Details
+- The model was fine-tuned in 4-bit precision using [unsloth](https://github.com/unslothai/unsloth)
 ## I prepared for you a Gradio App to do inference with the model and compare its results with the base llama3.1 model