Ibisbill
/

stage3_OpenThinker2-7B_lr_5e6

Text Generation

text-generation-inference

Model card Files Files and versions

Ibisbill commited on May 24

Commit

b3abf45

·

verified ·

1 Parent(s): 05dd6d9

Upload config

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/map-vepfs/ziyu/reasoning_tr/saves/stage3_7b_baseline/second_run/OpenThinker2-7B/stage3_combined_50k",
   "architectures": [
-    "Qwen2Model"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
@@ -21,7 +21,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_cache": false,
   "use_sliding_window": false,

 {
   "_name_or_path": "/map-vepfs/ziyu/reasoning_tr/saves/stage3_7b_baseline/second_run/OpenThinker2-7B/stage3_combined_50k",
   "architectures": [
+    "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
   "use_cache": false,
   "use_sliding_window": false,