End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+datasets: knoveleng/open-rs
 library_name: transformers
 model_name: DAPO-7B
 tags:
 - generated_from_trainer
-- trl
+- open-r1
 - dapo
+- trl
 licence: license
 ---
 
 # Model Card for DAPO-7B
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the [knoveleng/open-rs](https://huggingface.co/datasets/knoveleng/open-rs) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47969ecdc8316c40e6f959f6369d54cb33fa5660e1e4073f9f17e03ac0e208bd
-size 323014560
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7acf113b5afb31f6c395014a5891df9213109fa76ea978fd940f523c445b39c0
+oid sha256:b963806a9621b67998b79a6c4914859109c0c44beb65b5280a5366f1247b4786
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e38c04cca6a418ed413c932e303eec1886922e960cd068410e821338ad7178
+oid sha256:fbeeb996406d5efa81b92e118ad3ce20f681c79f26a20649df7afc3d367628d2
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ac7350e0ef280872dc11072e1a5ab14b8123b0347c603b525523a92b2091be
+oid sha256:1e028fffb56bad53f969cb4f661184cc9d68a8bc00fae957b590a5c8ae3cbd25
 size 4330865200