Instructions to use Maghrebi/abkhaz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maghrebi/abkhaz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Maghrebi/abkhaz")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Maghrebi/abkhaz") model = AutoModelForSeq2SeqLM.from_pretrained("Maghrebi/abkhaz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Maghrebi/abkhaz with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Maghrebi/abkhaz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Maghrebi/abkhaz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Maghrebi/abkhaz
- SGLang
How to use Maghrebi/abkhaz 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 "Maghrebi/abkhaz" \ --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": "Maghrebi/abkhaz", "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 "Maghrebi/abkhaz" \ --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": "Maghrebi/abkhaz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Maghrebi/abkhaz with Docker Model Runner:
docker model run hf.co/Maghrebi/abkhaz
Commit History
-
Update config.json
457be46 -
Update config.json
6f08fd7 -
Update README.md
92a93c8
-
Update tokenizer_config.json
f0fd352 -
Update config.json
ef69d2b
-
Update tokenizer_config.json
601d7cc -
Upload 2 files
cfa2eec -
Upload config.json
b5ccef5 -
Delete config.json
7331f69 -
Create config.json
5f58dda -
Update README.md
cd5ae9b -
Update README.md
3314c86 -
Update README.md
efd2b11 -
Update README.md
f28bc7d -
Update README.md
976705e -
Update README.md
5f9e911
-
Update README.md
0150849 -
Update README.md
2e740cf -
Update README.md
f88d6c0 -
Update README.md
f23f567 -
Update README.md
6d7e9d2 -
Update README.md
44a9766 -
Update README.md
6a2a180 -
Update README.md
23929a9 -
Upload 2 files
5a7a230 -
Update README.md
4e60fe1 -
initial commit
47368eb