v2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "output-small",
+  "_name_or_path": "microsoft/DialoGPT-small",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,6 +8,7 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -17,10 +18,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
@@ -28,16 +26,10 @@
   "summary_use_proj": true,
   "task_specific_params": {
     "conversational": {
-        "max_length":200,      
-        "no_repeat_ngram_size":3,       
-        "do_sample":true, 
-        "top_k":100, 
-        "top_p":0.7,
-        "temperature":0.8
+      "max_length": 1000
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.12.2",
-  "use_cache": false,
+  "transformers_version": "4.5.1",
+  "use_cache": true,
   "vocab_size": 50257
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d5d0a44e815587694cddcca48c0a93d52e2cae9370a9ca440f0c0101416346
-size 510401385
+oid sha256:b01e921afa4d202ec51b87870b7a96af20dc7976a2567383c850746f2e7dd80a
+size 510403817

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c2c95ba2743fc3d8cdbf71abde908369a5125d787da751207edb843d341111
-size 1391
+oid sha256:e6fa610da259cae1a376d6b5ae66fa72e4873d9ea870c6e6d1e27af759190391
+size 1327