tiny model

config.json

@@ -1,16 +1,21 @@
 {
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
   "initializer_range": 0.02,
   "intermediate_size": 512,
+  "layer_norm_eps": 1e-06,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
-  "model_type": "custom_llama_model",
+  "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 24,
   "num_key_value_heads": 4,
@@ -19,6 +24,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
   "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 32000

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bed5dd3516152db7423e1f915da3e6367b9f6a1459ba17ee779a5d4289fb124
+size 128524840