Trained with Unsloth

config.json

@@ -1,3 +1,42 @@
 {
-    "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": [
+    128001,
+    128008,
+    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": "4.46.3",
+  "unsloth_version": "2024.12.4",
+  "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 sha256:233e38b43fd109e918ec21ad7d8358671e5d1663b91ffdfaf4a4b5a0d1f4d74b
+oid sha256:3dcbb59ebecbaa45d099842fe46254d478ca3a10d0c0b38c6fae434fa5715cfc
 size 4965844039

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b090ff523e31ae2b7fb37e37ce1369720187aeaf4415ddaf53e894eab2d382
+oid sha256:7df16c722281897aa52889fe48b9751eaa2bae6aaf7eca707157daa165359699
 size 1459746080