Upload 5 files

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0",
+  "use_cache": false,
+  "vocab_size": 10000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1230d51db67d4116ed927f157bda640db1b56abc5354e58f1e1153370cc9d950
+size 114884584

training_config.json

@@ -0,0 +1,11 @@
+{
+  "d_model": 512,
+  "n_heads": 8,
+  "n_kv_heads": 4,
+  "n_layers": 6,
+  "max_seq_len": 512,
+  "device": "cuda",
+  "dataset_files": [
+    "cleaned_text.txt"
+  ]
+}