openai/gsm8k
Benchmark • Updated • 17.6k • 950k • 1.35k
How to use Swekerr/gsmma-270m-grpo with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Swekerr/gsmma-270m-grpo", dtype="auto")How to use Swekerr/gsmma-270m-grpo with Unsloth Studio:
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Swekerr/gsmma-270m-grpo to start chatting
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Swekerr/gsmma-270m-grpo to start chatting
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Swekerr/gsmma-270m-grpo to start chatting
pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="Swekerr/gsmma-270m-grpo",
max_seq_length=2048,
)Ran eval on random 100 Qs from gsm8k Got 1 correct. W.
This gemma3_text model was trained 2x faster with Unsloth and Huggingface's TRL library.