Text Generation
Transformers
Safetensors
English
pruned_flex_olmo
custom_code
math
pruned
distilled
mixture-of-experts
Instructions to use hbfreed/flex-math-8192 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hbfreed/flex-math-8192 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hbfreed/flex-math-8192", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("hbfreed/flex-math-8192", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hbfreed/flex-math-8192 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hbfreed/flex-math-8192" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hbfreed/flex-math-8192", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hbfreed/flex-math-8192
- SGLang
How to use hbfreed/flex-math-8192 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 "hbfreed/flex-math-8192" \ --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": "hbfreed/flex-math-8192", "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 "hbfreed/flex-math-8192" \ --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": "hbfreed/flex-math-8192", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hbfreed/flex-math-8192 with Docker Model Runner:
docker model run hf.co/hbfreed/flex-math-8192
| """Configuration for pruned FlexOlmo models with variable-width expert 1.""" | |
| from transformers import FlexOlmoConfig | |
| class PrunedFlexOlmoConfig(FlexOlmoConfig): | |
| """Config for FlexOlmo with a pruned expert 1. | |
| Extends FlexOlmoConfig with expert_1_intermediate_size to specify | |
| the width of the pruned expert. | |
| """ | |
| model_type = "pruned_flex_olmo" | |
| def __init__(self, expert_1_intermediate_size: int = None, **kwargs): | |
| super().__init__(**kwargs) | |
| # expert_1_intermediate_size: width of pruned expert 1 | |
| # If None, falls back to intermediate_size (no pruning) | |
| self.expert_1_intermediate_size = expert_1_intermediate_size or self.intermediate_size | |