Model save
Browse files- .gitignore +1 -0
- config.json +34 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- runs/Apr25_15-49-33_de96294fe16b/1682437783.5319464/events.out.tfevents.1682437783.de96294fe16b.24.1 +3 -0
- runs/Apr25_15-49-33_de96294fe16b/events.out.tfevents.1682437783.de96294fe16b.24.0 +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ClueAI/ChatYuan-large-v2",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoModel": "modeling_t5.T5ForConditionalGeneration"
|
8 |
+
},
|
9 |
+
"d_ff": 2816,
|
10 |
+
"d_kv": 64,
|
11 |
+
"d_model": 1024,
|
12 |
+
"decoder_start_token_id": 0,
|
13 |
+
"dense_act_fn": "gelu_new",
|
14 |
+
"dropout_rate": 0.1,
|
15 |
+
"eos_token_id": 1,
|
16 |
+
"feed_forward_proj": "gated-gelu",
|
17 |
+
"initializer_factor": 1.0,
|
18 |
+
"is_encoder_decoder": true,
|
19 |
+
"is_gated_act": true,
|
20 |
+
"layer_norm_epsilon": 1e-06,
|
21 |
+
"model_type": "t5",
|
22 |
+
"num_decoder_layers": 24,
|
23 |
+
"num_heads": 16,
|
24 |
+
"num_layers": 24,
|
25 |
+
"output_past": true,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"relative_attention_max_distance": 128,
|
28 |
+
"relative_attention_num_buckets": 32,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.26.1",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 32128
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.26.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78669de622421b4fc97b08ebddddec31cafe89f6ed42dbd0d722aec63a8b3f3f
|
3 |
+
size 3132793669
|
runs/Apr25_15-49-33_de96294fe16b/1682437783.5319464/events.out.tfevents.1682437783.de96294fe16b.24.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38aca2401a7704d0aceb1c8abe385ddc692029d9830a008ae98d169526d81927
|
3 |
+
size 5916
|
runs/Apr25_15-49-33_de96294fe16b/events.out.tfevents.1682437783.de96294fe16b.24.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb508bd60c40e83e29a7f7a63f5d2f02f0e77ff8d3ebac62e400e66caf1e5cd5
|
3 |
+
size 31828
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c2083a4dd8b56e99db4a408d68a50d4374252628247dbdc9d5931fddcf0a66d
|
3 |
+
size 742045
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"model_max_length": 2048,
|
6 |
+
"name_or_path": "ClueAI/ChatYuan-large-v2",
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"tokenizer_class": "T5Tokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dc77d6b0fb2f99287662a429faca710feee43ce2295f0fc3373e700580f143f
|
3 |
+
size 3707
|