Commit
•
8b2c899
1
Parent(s):
ee509f2
Add files
Browse files- .gitattributes +1 -4
- README.md +11 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
.gitattributes
CHANGED
@@ -9,14 +9,10 @@
|
|
9 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
*.model filter=lfs diff=lfs merge=lfs -text
|
11 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
14 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
15 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
16 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
17 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
20 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
21 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
22 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
@@ -29,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
9 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
*.model filter=lfs diff=lfs merge=lfs -text
|
11 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
12 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
13 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
14 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
15 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
16 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
17 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
18 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- eng
|
4 |
+
tags:
|
5 |
+
- integration
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
|
9 |
+
# BigScience - testing model
|
10 |
+
|
11 |
+
This model aims to test the conversion between Megatron-LM and transformers. It is a small ```GPT-2```-like model that has been used to debug the script. Use it only for integration tests
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf-internal-testing/tiny-random-bloom",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bias_dropout_fusion": true,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"dtype": "bfloat16",
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"hidden_dropout": 0.1,
|
13 |
+
"hidden_size": 64,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 8,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 2,
|
21 |
+
"pretraining_tp": 2,
|
22 |
+
"seq_length": 20,
|
23 |
+
"skip_bias_add": true,
|
24 |
+
"slow_but_exact": true,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.21.0.dev0",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 250880
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e22bceb559a5fcdc3dbb0f9ea622210cbe6b2a56d459ad7693284a1e99569c8
|
3 |
+
size 32322126
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
|
3 |
+
size 14500438
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast"}
|