Upload config

README.md

@@ -1,5 +1,7 @@
 ---
 base_model: Qwen/Qwen2.5-7B-Instruct
+datasets:
+- trl-lib/ultrafeedback_binarized
 library_name: transformers
 model_name: Qwen2.5-7B-DPO-2209
 tags:
@@ -7,8 +9,6 @@ tags:
 - trl
 - dpo
 licence: license
-datasets:
-- trl-lib/ultrafeedback_binarized
 ---
 
 # Model Card for Qwen2.5-7B-DPO-2209

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}