2.4835708502609366

config.json

@@ -7,15 +7,15 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 64,
+  "hidden_size": 132,
   "initializer_range": 0.02,
-  "intermediate_size": 256,
+  "intermediate_size": 528,
   "max_position_embeddings": 128,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 1,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 1,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
   "pad_token_id": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
@@ -25,5 +25,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 3200
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c114aa61dfa5c8ee14e6dfac5d448812fc73c14112d54b17fcf53521a9dedce
-size 2166160
+oid sha256:5649a03ab13ed28954e0b594c89ac7be160fc470e0f107ae14fdba068de710ab
+size 38261520