Upload model

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "crumb/25m-special",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ALMHeadModel"
+  ],
+  "attn_bias": false,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "crumb/25m-special--configuration_gpt2a.GPT2AConfig",
+    "AutoModelForCausalLM": "crumb/25m-special--modeling_gpt2a.GPT2ALMHeadModel"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "full_layer_repetitions": 4,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-06,
+  "mlp_bias": false,
+  "model_type": "gpt2a",
+  "n_ctx": 2048,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "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": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 50277
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.34.1",
+  "use_cache": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63712c88472c5413ecd021221e0f8f97ff41de11d69cae9b138b1eed0f58dfa
+size 203726915