Trained with Unsloth

config.json

@@ -1,3 +1,39 @@
 {
-    "model_type": "llama"
-}
+  "_name_or_path": "unsloth/llama-3.2-3b-instruct-bnb-4bit",
+  "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": "2025.2.15",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.48.2"
+  "transformers_version": "4.49.0"
 }

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68af43b49ed7530e6b167a6869a13bc2729b6b9c77b05da01ebb65a0b822db5
+oid sha256:32ce09d19db3ffeab40050352fcfeb3976c6785eeb5274e34d057ce5d15571c3
 size 4965844039

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc6982475959f6390083d6262610a12920af143c3b7cb43367de708304f60978
+oid sha256:6c5e7b7d20ba9b5540b9faf67551c2d5ce69b9663b706b19d8011e0cbfca2e90
 size 1459746080