(Trained with Unsloth)

config.json

@@ -5,14 +5,14 @@
   "attention_dropout": 0.0,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 8960,
+  "intermediate_size": 4864,
   "max_position_embeddings": 32768,
   "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5bc82e596e69ee9fad9e160a25587b2310e1508bbf97edf546d3ad30684770
-size 3087467144
+oid sha256:82aca9647d513d08fe7ab336135f76d6468d59fd1ee986388e0aa63e85fb61a7
+size 988097824

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:873f9c3d5e28877c9915f09c76bbfc8a0b7ae244781692ab2b0877873b918022
+size 11421996