init
Browse files- config.json +4 -4
- eval_results.txt +1 -1
- pytorch_model.bin +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "microsoft/DialoGPT-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -12,10 +12,10 @@
|
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
"n_ctx": 1024,
|
15 |
-
"n_embd":
|
16 |
-
"n_head":
|
17 |
"n_inner": null,
|
18 |
-
"n_layer":
|
19 |
"n_positions": 1024,
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-large",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
"n_ctx": 1024,
|
15 |
+
"n_embd": 1280,
|
16 |
+
"n_head": 20,
|
17 |
"n_inner": null,
|
18 |
+
"n_layer": 36,
|
19 |
"n_positions": 1024,
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(
|
|
|
1 |
+
perplexity = tensor(2.4841)
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea9bc797eed0a0cdea4753d5bbb78721d7eb4c7574319a15fdc90907179b115f
|
3 |
+
size 3134045897
|
tokenizer_config.json
CHANGED
@@ -1 +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-
|
|
|
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-large", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d4c86913f4b018d43aeee25bfc607ac9f55fe5132a062b6f0cc486d740ef5c1
|
3 |
size 1327
|