Trained with Unsloth

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "notzero/modelcombinedgrpo",
+  "_name_or_path": "notzero/qwen1_5b",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
+  "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
@@ -26,6 +26,7 @@
   "unsloth_fixed": true,
   "unsloth_version": "2025.2.15",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,15 +1,8 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
+  "eos_token_id": 151643,
   "max_length": 32768,
+  "max_new_tokens": 2048,
   "pad_token_id": 151654,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
   "transformers_version": "4.49.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4b55b9a2208edea8cb6bad3087a6023364e2137abaf60b1436d2a5c00d4264
+oid sha256:918d0c78f3cca11c1bd209f7afc6418f562a0796f0bf81e0c2c8e938101b610d
 size 3087542290