Trained with Unsloth

config.json

@@ -1,3 +1,32 @@
 {
-    "model_type": "qwen2"
-}
+  "_name_or_path": "unsloth/Qwen2.5-0.5B-bnb-4bit",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151665,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "unsloth_version": "2024.9.post4",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -4,5 +4,5 @@
   "max_length": 32768,
   "max_new_tokens": 2048,
   "pad_token_id": 151665,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22a8006d3642dcc751e922ce803bacfae9e55f83398994fae0a1f3aed271696
+oid sha256:e8acb27b17e061ce9b1603ce02afe99d1c9a111d2e36663e37f9dd8afdc2de06
 size 988097824