Upload 8 files

More training on separation

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/DialoGPT-small",
+  "_name_or_path": "jinymusim/gpt-czech-poet",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,6 +8,7 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "eos_token_ids": 0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -17,7 +18,8 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 50256,
+  "output_past": true,
+  "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -28,12 +30,13 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "task_specific_params": {
-    "conversational": {
-      "max_length": 1000
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.29.2",
   "use_cache": true,
-  "vocab_size": 50261
+  "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.28.1"
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:813dc820124ee5bbf050b6d54ef5ee549cc2f54d69138ab1ad740c352b5e0c7d
-size 510410301
+oid sha256:fd9305b647f3049770f9661cb3acb2aec7b0a2f0d6eda193e90a8e28379f42dc
+size 510398013

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "additional_special_tokens": [
-    "<|system|>",
-    "<|user|>",
-    "<|endoftext|>",
-    "<|belive|>"
-  ],
-  "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
-  },
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
   "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -20,7 +20,14 @@
   },
   "errors": "replace",
   "model_max_length": 1024,
-  "pad_token": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": {
     "__type": "AddedToken",