Upload model

config.json

@@ -1,26 +1,24 @@
 {
-  "_name_or_path": "jonfd/gpt2-igc-is",
+  "_name_or_path": "models/jonas-hallgrimsson-gpt2/checkpoint-5000",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.0,
-  "bos_token_id": 50256,
-  "do_sample": true,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 50256,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 51000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 51000,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "max_length": 50,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 512,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
+  "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
@@ -28,14 +26,8 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
   "torch_dtype": "float32",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
-  "vocab_size": 51000
+  "vocab_size": 51001
 }

generation_config.json

@@ -1,8 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "do_sample": true,
-  "eos_token_id": 50256,
-  "max_length": 50,
+  "bos_token_id": 51000,
+  "eos_token_id": 51000,
+  "pad_token_id": 51000,
   "transformers_version": "4.37.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53a5fa05a5ecd028da74d5fc3a09debcf060aba3a275f5155548a860f1a8e3c
-size 500056704
+oid sha256:50dc5de325e72791733b805ac7463750687463fdf7488afaef2bc826183a6340
+size 500059776