Instructions to use houssamboukhalfa/Nojoom-AQL-42B-PT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use houssamboukhalfa/Nojoom-AQL-42B-PT with Transformers:

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

pipe = pipeline("text-generation", model="houssamboukhalfa/Nojoom-AQL-42B-PT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("houssamboukhalfa/Nojoom-AQL-42B-PT")
model = AutoModelForCausalLM.from_pretrained("houssamboukhalfa/Nojoom-AQL-42B-PT", device_map="auto")
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 houssamboukhalfa/Nojoom-AQL-42B-PT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "houssamboukhalfa/Nojoom-AQL-42B-PT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "houssamboukhalfa/Nojoom-AQL-42B-PT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/houssamboukhalfa/Nojoom-AQL-42B-PT

SGLang

How to use houssamboukhalfa/Nojoom-AQL-42B-PT 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 "houssamboukhalfa/Nojoom-AQL-42B-PT" \
    --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": "houssamboukhalfa/Nojoom-AQL-42B-PT",
		"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 "houssamboukhalfa/Nojoom-AQL-42B-PT" \
        --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": "houssamboukhalfa/Nojoom-AQL-42B-PT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use houssamboukhalfa/Nojoom-AQL-42B-PT with Docker Model Runner:
```
docker model run hf.co/houssamboukhalfa/Nojoom-AQL-42B-PT
```

Nojoom-AQL-42B-PT

This repository republishes the model files from:

Changes made

Repository renamed to Nojoom-AQL-42B-PT
Safe metadata fields updated where applicable
README replaced
Architecture, vocabulary, tensor names, and shard mappings left unchanged

Attribution

Please review the original source repository for model details, training information, intended use, and limitations.

License

This repository preserves the source model's declared license.

Downloads last month: 9

Safetensors

Model size

41B params

Tensor type

BF16