20 lines
668 B
Markdown
20 lines
668 B
Markdown
---
|
|
base_model: atomwalk12/LinalgZero-SFT
|
|
library_name: peft
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- base_model:adapter:atomwalk12/LinalgZero-SFT
|
|
- grpo
|
|
- lora
|
|
- transformers
|
|
- trl
|
|
- unsloth
|
|
- step1000
|
|
---
|
|
|
|
# Model Card for LinalgZero-GSPO
|
|
|
|
Information and code used to train this model is available [on Github](https://github.com/atomwalk12/linalg-zero).
|
|
|
|
This model is a fine-tuned version of [atomwalk12/LinalgZero-SFT](https://huggingface.co/atomwalk12/LinalgZero-SFT) on the [atomwalk12/linalgzero-grpo](https://huggingface.co/datasets/atomwalk12/linalgzero-grpo) dataset using the GSPO algorithm.
|
|
It has been trained using [ART](https://deepwiki.com/OpenPipe/ART). |