(Trained with Unsloth)

config.json

@@ -0,0 +1,32 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 50256,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 50256,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 2752,
+    "max_position_embeddings": 1024,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 8,
+    "pad_token_id": 50256,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "unsloth_version": "2026.4.4",
+    "use_cache": false,
+    "vocab_size": 50257
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}