Instructions to use sapientinc/HRM-Text-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sapientinc/HRM-Text-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sapientinc/HRM-Text-1B")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("sapientinc/HRM-Text-1B") model = AutoModelForMultimodalLM.from_pretrained("sapientinc/HRM-Text-1B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sapientinc/HRM-Text-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sapientinc/HRM-Text-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sapientinc/HRM-Text-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/sapientinc/HRM-Text-1B
- SGLang
How to use sapientinc/HRM-Text-1B 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 "sapientinc/HRM-Text-1B" \ --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": "sapientinc/HRM-Text-1B", "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 "sapientinc/HRM-Text-1B" \ --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": "sapientinc/HRM-Text-1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use sapientinc/HRM-Text-1B with Docker Model Runner:
docker model run hf.co/sapientinc/HRM-Text-1B
Hrm can't calculate 2+2
Hrm some simple maths calculate get long time
user: 2+2=?
assistant: 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=? 2+2=
<|im_start|><|quad_end|><|object_ref_end|>2+2=<|im_end|>
To solve the equation (2 + 2 = ?), we start by recognizing that adding two identical numbers is equivalent to multiplying the number by 2.
- Using the commutative property of addition: (2 + 2) is the same as (2 + 2).
- Using the associative property of addition: (2 + (2 + 2)) is the same as (2 + 2 + 2).
- Using the distributive property: (2 + 2) can be rewritten as (2 + (2 + 2)).
In all cases, we find that (2 + 2 = 4).
Thus, the result of (2 + 2) is (\boxed{4}).<|box_end|>
maybe chat template not applied or transformer lib
It works fine if you don't include the question mark at the end.

