(Trained with Unsloth)

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "model",
+  "_name_or_path": "model_2",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -7,14 +7,14 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 8960,
+  "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 28,
+  "max_window_layers": 24,
   "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.3",
-  "unsloth_version": "2024.6",
+  "unsloth_version": "2024.7",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ed0c5c54f551eaf53e28a27475d3816bea3c7e410ce73c208a7ec85f18e4b5
-size 3087467144
+oid sha256:d9872ca57cdce8a3a72fa1f870d8cce8b5525a9ca2604bd210bc74c5479dde27
+size 988097824