v2

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  "<bot>:": 50261,
+  "<endofstring>": 50260,
+  "<startofstring>": 50259,
+  "<|endoftext|>": 50257,
+  "<|pad|>": 50258,
+  "<|startoftext|>": 50256
+}

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "microsoft/DialoGPT-small",
+  "_name_or_path": "C:/Users/erikycd/Documents/Python offline/GPT2_esp/model_flaxcom_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
+  "attn_pdrop": 0.0,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -18,7 +19,7 @@
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
+  "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
@@ -27,12 +28,13 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "task_specific_params": {
-    "conversational": {
-      "max_length": 30
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.20.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50262
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b315a2e10263aefe51a50a1fab882e1865de2b175ef83bfad34018622ae4ad
-size 510396521
+oid sha256:b0b3a48552dd486b496cd7b010a23565165e253783e9f91073ffa9475ed1af92
+size 510411881

special_tokens_map.json

@@ -1,23 +1,6 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<startofstring>",
+  "eos_token": "<endofstring>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,34 +1,10 @@
 {
-  "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 1024,
-  "name_or_path": "microsoft/DialoGPT-small",
-  "pad_token": null,
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "C:/Users/erikycd/Documents/Python offline/GPT2_esp/model_flaxcom_gpt2",
+  "pad_token": "<|pad|>",
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }