Trained with Unsloth

config.json

@@ -1,3 +1,39 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.49.0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.9",
+  "use_cache": true,
+  "vocab_size": 128256
+}

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b0814d3106218c8d027d9005fa42db7d2e4acfab219d7a603459021a42b455
+oid sha256:d0ed2c2a4d250ae9f85d60b5bee2fab9e67e30ad2af01990f5b5520a0ab66b71
 size 4965844039

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e26dd54e9964adc8c32dc065d8da2db756bae57258b107c6f05c5a39eff384
+oid sha256:60652e07165cc095499a025d7c35f32b89a2eff6413cc13df15b87c1b7230f70
 size 1459746080