First commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-10500/config.json +37 -0
- checkpoint-10500/merges.txt +0 -0
- checkpoint-10500/optimizer.pt +3 -0
- checkpoint-10500/pytorch_model.bin +3 -0
- checkpoint-10500/scheduler.pt +3 -0
- checkpoint-10500/special_tokens_map.json +1 -0
- checkpoint-10500/tokenizer.json +0 -0
- checkpoint-10500/tokenizer_config.json +1 -0
- checkpoint-10500/training_args.bin +3 -0
- checkpoint-10500/vocab.json +0 -0
- checkpoint-14000/config.json +37 -0
- checkpoint-14000/merges.txt +0 -0
- checkpoint-14000/optimizer.pt +3 -0
- checkpoint-14000/pytorch_model.bin +3 -0
- checkpoint-14000/scheduler.pt +3 -0
- checkpoint-14000/special_tokens_map.json +1 -0
- checkpoint-14000/tokenizer.json +0 -0
- checkpoint-14000/tokenizer_config.json +1 -0
- checkpoint-14000/training_args.bin +3 -0
- checkpoint-14000/vocab.json +0 -0
- checkpoint-17500/config.json +37 -0
- checkpoint-17500/merges.txt +0 -0
- checkpoint-17500/optimizer.pt +3 -0
- checkpoint-17500/pytorch_model.bin +3 -0
- checkpoint-17500/scheduler.pt +3 -0
- checkpoint-17500/special_tokens_map.json +1 -0
- checkpoint-17500/tokenizer.json +0 -0
- checkpoint-17500/tokenizer_config.json +1 -0
- checkpoint-17500/training_args.bin +3 -0
- checkpoint-17500/vocab.json +0 -0
- checkpoint-21000/config.json +37 -0
- checkpoint-21000/merges.txt +0 -0
- checkpoint-21000/optimizer.pt +3 -0
- checkpoint-21000/pytorch_model.bin +3 -0
- checkpoint-21000/scheduler.pt +3 -0
- checkpoint-21000/special_tokens_map.json +1 -0
- checkpoint-21000/tokenizer.json +0 -0
- checkpoint-21000/tokenizer_config.json +1 -0
- checkpoint-21000/training_args.bin +3 -0
- checkpoint-21000/vocab.json +0 -0
- checkpoint-24500/config.json +37 -0
- checkpoint-24500/merges.txt +0 -0
- checkpoint-24500/optimizer.pt +3 -0
- checkpoint-24500/pytorch_model.bin +3 -0
- checkpoint-24500/scheduler.pt +3 -0
- checkpoint-24500/special_tokens_map.json +1 -0
- checkpoint-24500/tokenizer.json +0 -0
- checkpoint-24500/tokenizer_config.json +1 -0
- checkpoint-24500/training_args.bin +3 -0
- checkpoint-24500/vocab.json +0 -0
checkpoint-10500/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.10.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
checkpoint-10500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb71a52029bc13013b55eca802f12699ad2df12bbcba1de2524f442621d8460f
|
3 |
+
size 995604017
|
checkpoint-10500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ea39de1437ef62dae22fa72f888a55e7e5561a3753f5915ddeddfb1c4703445
|
3 |
+
size 510403817
|
checkpoint-10500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a3c074a5b5bdeb52ae559f03ddd89f63086d78922407a8e83cbc7ece3e9cd2
|
3 |
+
size 623
|
checkpoint-10500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
checkpoint-10500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10500/tokenizer_config.json
ADDED
@@ -0,0 +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"}
|
checkpoint-10500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaff6978399fc6716c6a99d873c09e3506350e294e0ae3988336802cee250ac
|
3 |
+
size 1327
|
checkpoint-10500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.10.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
checkpoint-14000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:929abb5b89868b30ac1749ab48c82efb25cbf7f2b2e35749faa67997eddf4a63
|
3 |
+
size 995604017
|
checkpoint-14000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a2f183631c221c49d5734fca84a90c05e9603ae8606225d6d9eb63fbc9448c
|
3 |
+
size 510403817
|
checkpoint-14000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b97bfdbb8e78e5e0b5bae7fe9e4c7a6975ce177b3dead101ccb44ab6154681e2
|
3 |
+
size 623
|
checkpoint-14000/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
checkpoint-14000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-14000/tokenizer_config.json
ADDED
@@ -0,0 +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"}
|
checkpoint-14000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaff6978399fc6716c6a99d873c09e3506350e294e0ae3988336802cee250ac
|
3 |
+
size 1327
|
checkpoint-14000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-17500/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.10.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
checkpoint-17500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-17500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56023f277f43605801d3c325baea6ff83229d525cee6c082da765165d9434541
|
3 |
+
size 995604017
|
checkpoint-17500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a7f0967783018081ece314015af1907cbb39e69a7b024a85e72b3c19024a37
|
3 |
+
size 510403817
|
checkpoint-17500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dd361166f1f5ea7d6bbc33773c64b20309571af0fa6cf9b11f3a56450c4c346
|
3 |
+
size 623
|
checkpoint-17500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
checkpoint-17500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-17500/tokenizer_config.json
ADDED
@@ -0,0 +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"}
|
checkpoint-17500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaff6978399fc6716c6a99d873c09e3506350e294e0ae3988336802cee250ac
|
3 |
+
size 1327
|
checkpoint-17500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-21000/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.10.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
checkpoint-21000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-21000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c68710cbf58f6677b191c8ae8071389e5d00da1f202303af1458767ff9c924eb
|
3 |
+
size 995604017
|
checkpoint-21000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7312f3e6033ea81e5769ba39afa20cc966a1988234f7e169e4d65d21170a183
|
3 |
+
size 510403817
|
checkpoint-21000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e608622907e9ddce213ec42556c6bd7f583f75eebe8081944201c3873a9dd82f
|
3 |
+
size 623
|
checkpoint-21000/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
checkpoint-21000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-21000/tokenizer_config.json
ADDED
@@ -0,0 +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"}
|
checkpoint-21000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaff6978399fc6716c6a99d873c09e3506350e294e0ae3988336802cee250ac
|
3 |
+
size 1327
|
checkpoint-21000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-24500/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"task_specific_params": {
|
29 |
+
"conversational": {
|
30 |
+
"max_length": 1000
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.10.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50257
|
37 |
+
}
|
checkpoint-24500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-24500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d113ab65724f3201eb80f146236016ad81d217958ef63c39f6d90d56b0dff3a
|
3 |
+
size 995604017
|
checkpoint-24500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508554f84c9ea2acef5ed4ad82831b89db29a1cae01eea4882d36550c7a15091
|
3 |
+
size 510403817
|
checkpoint-24500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75872573d2b05d48b39d6b27a3ac3938fc878a69bf14b9fe3d844dd9e8684560
|
3 |
+
size 623
|
checkpoint-24500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
checkpoint-24500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-24500/tokenizer_config.json
ADDED
@@ -0,0 +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"}
|
checkpoint-24500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaff6978399fc6716c6a99d873c09e3506350e294e0ae3988336802cee250ac
|
3 |
+
size 1327
|
checkpoint-24500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|