Instructions to use 123sg/MacroCoverageLM-Release with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 123sg/MacroCoverageLM-Release with Transformers:

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

pipe = pipeline("text-generation", model="123sg/MacroCoverageLM-Release")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("123sg/MacroCoverageLM-Release")
model = AutoModelForCausalLM.from_pretrained("123sg/MacroCoverageLM-Release", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 123sg/MacroCoverageLM-Release with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "123sg/MacroCoverageLM-Release"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "123sg/MacroCoverageLM-Release",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/123sg/MacroCoverageLM-Release

SGLang

How to use 123sg/MacroCoverageLM-Release 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 "123sg/MacroCoverageLM-Release" \
    --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": "123sg/MacroCoverageLM-Release",
		"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 "123sg/MacroCoverageLM-Release" \
        --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": "123sg/MacroCoverageLM-Release",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 123sg/MacroCoverageLM-Release with Docker Model Runner:
```
docker model run hf.co/123sg/MacroCoverageLM-Release
```

MacroCoverageLM-1B

1. Introduction

MacroCoverageLM-1B is an open checkpoint family trained for broad-coverage reasoning. Every checkpoint in this release comes from the same pretraining run and differs only in how many optimisation steps it received.

The release reports the run the process selected, with each benchmark suite weighted equally.

2. Evaluation Results

Comprehensive Benchmark Results

	Benchmark	Base-1B	Chat-1B	MacroCoverageLM-1B-Small	MacroCoverageLM-1B
Core Reasoning Tasks	Math Reasoning	0.548	0.561	0.572	0.450
	Logical Reasoning	0.548	0.561	0.572	0.450
	Common Sense	0.548	0.561	0.572	0.700
Language Understanding	Reading Comprehension	0.548	0.561	0.572	0.700
	Question Answering	0.548	0.561	0.572	0.450
	Text Classification	0.548	0.561	0.572	0.700
	Sentiment Analysis	0.548	0.561	0.572	0.700
Generation Tasks	Code Generation	0.548	0.561	0.572	0.450
	Creative Writing	0.548	0.561	0.572	0.700
	Dialogue Generation	0.548	0.561	0.572	0.700
	Summarization	0.548	0.561	0.572	0.700
Specialized Capabilities	Translation	0.548	0.561	0.572	0.700
	Knowledge Retrieval	0.548	0.561	0.572	0.700
	Instruction Following	0.548	0.561	0.572	0.450
	Safety Evaluation	0.548	0.561	0.572	0.450

Overall Performance Summary

Scores are the equal-weight mean over the fifteen suites. Each cell is the accuracy over the full held-out split.

Downloads last month: 67