End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+datasets: knoveleng/open-rs
 library_name: transformers
 model_name: DAPO-8B
 tags:
 - generated_from_trainer
-- trl
+- open-r1
 - dapo
+- trl
 licence: license
 ---
 
 # Model Card for DAPO-8B
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) 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:ed5057e58d9c86f27f25bff17f93ec31710991515dde331e78b702be3b250793
-size 335605144
+oid sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
+size 40

config.json

@@ -18,6 +18,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128001,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {

generation_config.json

@@ -2,7 +2,10 @@
   "_from_model_config": true,
   "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": 128001,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.95,
   "transformers_version": "4.57.1"

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c984f65c9eedc58fe094e25c972d3709f8cddf1340fed3ebce67c17afbe06c
+oid sha256:9f30f112920d1e7b4852aa1a8523b5318ceaeadc79ccbb259c8ce88affedff3f
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a030a1b0b2b180923fa99a8b0296488c5e16daa53c33ebb8f0d6fbc2a6b2dc1
+oid sha256:ad8d9d161c36affea92f78179b228855b0d53f921b4bb4c773cf06fd8d657391
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b546fd3f6d8c9d12ac6ff2199aa18b6f14b3970dda812f2325b38cda62b1c91
+oid sha256:a2427ec8e0f491bb265bd37a808b85655ce1bdd7d17f223a48ef547154cbd8f5
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce2f3c51b0f3f003535366a56f9348f58eeb46c3b8eee8217b7346bd5352ec9
+oid sha256:f0622c5d71a8f922509f93ebaceb413ad5277c8bce1b81800d679262b910e8d3
 size 1168138808