Blancy
/

Qwen3-1.7B-Open-R1-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Blancy commited on Jun 23, 2025

Commit

4803e6c

·

verified ·

1 Parent(s): 6788e02

Training in progress, epoch 1

Files changed (3) hide show

config.json +2 -2
model.safetensors +2 -2
training_args.bin +2 -2

config.json CHANGED Viewed

@@ -8,9 +8,9 @@
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "max_position_embeddings": 40960,
   "max_window_layers": 28,
   "model_type": "qwen3",

   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
+  "intermediate_size": 6144,
   "max_position_embeddings": 40960,
   "max_window_layers": 28,
   "model_type": "qwen3",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e278cefd4f6167533ecad436e93a66b66e44f9c73c5c553818bdbd134022c0c8
-size 1503300328

 version https://git-lfs.github.com/spec/v1
+oid sha256:0b71093e6db03bd1ceb904cc0b7c9ef18df4f6f51aeada400c42a3208b83619a
+size 4063515640

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6b3a7f05b03cfbc508e543e5bc45cf7eb43ea153764d2e86389e5ed37655ab
-size 8056

 version https://git-lfs.github.com/spec/v1
+oid sha256:4692034c27fa7cd89e2cec300c8d71269df0279267137a575cc66c992c60fa9f
+size 7992