init upload config.json

config.json

@@ -1,37 +1,31 @@
 {
-  "_name_or_path": "/mnt/ph/ScaleIF/verl/examples/grpo_trainer/checkpoints/verl_grpo_if/tulu3_8b_if_3_3/global_step_200/actor/huggingface",
+  "_name_or_path": "/mnt/ph/ScaleIF/verl/examples/grpo_trainer/checkpoints/verl_grpo_if/r1_qwen25_7b_if_3_12/global_step_550/actor/huggingface",
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 128,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 3584,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 18944,
   "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 128256,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 8.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
   "use_cache": true,
-  "vocab_size": 128264
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
 }