Trained with Unsloth

config.json

@@ -1,15 +1,16 @@
 {
-  "_name_or_path": "notzero/qwen1_5b",
+  "_name_or_path": "notzero/model_combined",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "eos_token_id": 151645,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 24576,
   "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 12,
@@ -18,14 +19,15 @@
   "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
+  "rope_theta": 10000,
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.47.1",
   "unsloth_fixed": true,
   "unsloth_version": "2025.1.8",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,15 +1,11 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 151646,
   "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "max_length": 32768,
+  "eos_token_id": 151643,
+  "max_length": 24576,
   "pad_token_id": 151654,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "temperature": 0.6,
+  "top_p": 0.95,
   "transformers_version": "4.47.1"
 }