GSM8k-GRPO
Collection
26 items • Updated
gsm8k-nemotron-mini-4b-instruct-rajat-seed-42-G-16
LoRA adapter fine-tuned from nvidia/Nemotron-Mini-4B-Instruct on GSM8K using GRPO.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("rghosh8/gsm8k-nemotron-mini-4b-instruct-rajat-seed-42-G-16", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("rghosh8/gsm8k-nemotron-mini-4b-instruct-rajat-seed-42-G-16")
- Downloads last month
- 5
Model tree for rghosh8/gsm8k-nemotron-mini-4b-instruct-rajat-seed-42-G-16
Base model
nvidia/Nemotron-Mini-4B-Instruct