Upload model

config.json

@@ -0,0 +1,37 @@
+{
+  "PET": null,
+  "_name_or_path": "./dst192",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "flash_attn": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "low_rank": null,
+  "model_type": "gpt2",
+  "n_embd": 384,
+  "n_head": 6,
+  "n_inner": 1536,
+  "n_layer": 192,
+  "n_positions": 1024,
+  "qkvo_attn": 144,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "sigma_reparam": null,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b271f1d3b11bc82914c2ec23866f1faa1506c894d2094a73442a77d8380b6b6d
+size 1897519248