Upload initial model config and tokenizer (no PEFT, no training performed)

config.json

@@ -1,9 +1,9 @@
 {
-  "activation_function": "gelu_new",
+  "activation_function": "silu",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
+  "attn_pdrop": 0.0,
   "bos_token_id": 0,
   "embd_pdrop": 0.1,
   "eos_token_id": 2,
@@ -11,8 +11,8 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 32000,
-  "n_embd": 128,
-  "n_head": 4,
+  "n_embd": 192,
+  "n_head": 2,
   "n_inner": null,
   "n_layer": 1,
   "n_positions": 32000,
@@ -26,8 +26,9 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 261
 }

generation_config.json

@@ -3,5 +3,6 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.51.3"
+  "transformers_version": "4.51.3",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6992589cfc8bd7d255c1d64002beece225922e1dab348c970839944df654f2e4
-size 17313280
+oid sha256:97bc19cdef5742ce7d1a365c168f10e30fcb536dff98f38bebf07d85a70bf1ab
+size 26759520