Instructions to use osunlp/ARLoop-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use osunlp/ARLoop-1.2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="osunlp/ARLoop-1.2B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("osunlp/ARLoop-1.2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use osunlp/ARLoop-1.2B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "osunlp/ARLoop-1.2B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "osunlp/ARLoop-1.2B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/osunlp/ARLoop-1.2B
- SGLang
How to use osunlp/ARLoop-1.2B 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 "osunlp/ARLoop-1.2B" \ --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": "osunlp/ARLoop-1.2B", "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 "osunlp/ARLoop-1.2B" \ --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": "osunlp/ARLoop-1.2B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use osunlp/ARLoop-1.2B with Docker Model Runner:
docker model run hf.co/osunlp/ARLoop-1.2B
Download config.json from osunlp/ARLoop-1.2B: direct link, hf CLI and curl.
- Browser
- Download file 871 Bytes
-
https://huggingface.co/osunlp/ARLoop-1.2B/resolve/main/config.json
- Command line
-
hf download hf://osunlp/ARLoop-1.2B/config.json
-
curl -L -o config.json https://huggingface.co/osunlp/ARLoop-1.2B/resolve/main/config.json
871 Bytes
| { | |
| "architectures": [ | |
| "ARLoopForCausalLM" | |
| ], | |
| "attnres_block_size": 24, | |
| "auto_map": { | |
| "AutoConfig": "configuration_arloop.ARLoopConfig", | |
| "AutoModelForCausalLM": "modeling_arloop.ARLoopForCausalLM" | |
| }, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "embedding_scale": 1.0, | |
| "eos_token_id": 0, | |
| "head_dim": 128, | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "logit_softcap": null, | |
| "loop_count": 3, | |
| "max_position_embeddings": 4096, | |
| "model_type": "arloop", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 72, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "physical_layers": 24, | |
| "qk_norm": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_condense_ratio": 1, | |
| "rope_theta": 50000, | |
| "sw_blocks": 3, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.12.1", | |
| "use_cache": true, | |
| "vocab_size": 49152, | |
| "torch_dtype": "bfloat16" | |
| } | |