Upload folder using huggingface_hub
Browse files- config.json +28 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RetNetModelWithLMHead"
|
4 |
+
],
|
5 |
+
"chunk_size": 512,
|
6 |
+
"eos_token_id": 0,
|
7 |
+
"ffn_proj_size": 1024,
|
8 |
+
"forward_impl": "parallel",
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"is_decoder": true,
|
12 |
+
"model_type": "retnet",
|
13 |
+
"num_heads": 8,
|
14 |
+
"num_layers": 12,
|
15 |
+
"output_retentions": false,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qk_dim": 512,
|
18 |
+
"torch_dtype": "float32",
|
19 |
+
"transformers_version": "4.33.3",
|
20 |
+
"unk_token_id": 0,
|
21 |
+
"use_bias_in_mlp": true,
|
22 |
+
"use_bias_in_msr": false,
|
23 |
+
"use_bias_in_msr_out": false,
|
24 |
+
"use_cache": true,
|
25 |
+
"use_default_gamma": false,
|
26 |
+
"v_dim": 1024,
|
27 |
+
"vocab_size": 50432
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 0,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.33.3"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b549356447aff95d69f881788d6438ff2ba2984efa9e9b482b510e756f4b8ccc
|
3 |
+
size 255483461
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:231684151ed6f83839f5fb255cf595bcebe7fe6e4e16d050841871b0250bd2c3
|
3 |
+
size 508916993
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7da54546bf15f018995bca80db587d4755e5247e40bd8916fc403c316c19a44b
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f2af49cd78aa75693b66111f64af3edc603f1233d3d799649e9c475f74d7e86
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:334d2fd16df7e6bda369a22aa6daf4aed97e40086063cc7f1979765bf12670c1
|
3 |
+
size 4027
|