---
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- grpo
- gsm8k
- math
- lora
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
---

# gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-16_merged

Merged model fine-tuned from [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on GSM8K using GRPO.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-16_merged", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("rghosh8/gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-3407-G-16_merged")
```