Upload tiny models for XGLMForCausalLM
Browse files- config.json +30 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +17 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "temp/dummy/xglm/XGLMForCausalLM",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"XGLMForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"attention_heads": 4,
|
| 10 |
+
"bos_token_id": 0,
|
| 11 |
+
"d_model": 32,
|
| 12 |
+
"decoder_start_token_id": 2,
|
| 13 |
+
"dropout": 0.1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"ffn_dim": 37,
|
| 16 |
+
"gradient_checkpointing": false,
|
| 17 |
+
"init_std": 0.02,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"is_decoder": true,
|
| 20 |
+
"layerdrop": 0.0,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"model_type": "xglm",
|
| 23 |
+
"num_layers": 5,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"scale_embedding": true,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.25.0.dev0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 1024
|
| 30 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:716441d567fd6aa8807b5ee1f8a312324a8ef276c8a4da6999276cba10e82d14
|
| 3 |
+
size 292714
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<madeupword0>",
|
| 4 |
+
"<madeupword1>",
|
| 5 |
+
"<madeupword2>",
|
| 6 |
+
"<madeupword3>",
|
| 7 |
+
"<madeupword4>",
|
| 8 |
+
"<madeupword5>",
|
| 9 |
+
"<madeupword6>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": "<s>",
|
| 12 |
+
"cls_token": "<s>",
|
| 13 |
+
"eos_token": "</s>",
|
| 14 |
+
"pad_token": "<pad>",
|
| 15 |
+
"sep_token": "</s>",
|
| 16 |
+
"unk_token": "<unk>"
|
| 17 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f8d5af1b7033f94eab5e5fe562f25b08c70fc4c17206d209c37577b6d4b404b
|
| 3 |
+
size 560936
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<madeupword0>",
|
| 4 |
+
"<madeupword1>",
|
| 5 |
+
"<madeupword2>",
|
| 6 |
+
"<madeupword3>",
|
| 7 |
+
"<madeupword4>",
|
| 8 |
+
"<madeupword5>",
|
| 9 |
+
"<madeupword6>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": "<s>",
|
| 12 |
+
"cls_token": "<s>",
|
| 13 |
+
"eos_token": "</s>",
|
| 14 |
+
"model_max_length": 512,
|
| 15 |
+
"name_or_path": "facebook/xglm-564M",
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"sp_model_kwargs": {},
|
| 19 |
+
"special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json",
|
| 20 |
+
"tokenizer_class": "XGLMTokenizer",
|
| 21 |
+
"unk_token": "<unk>"
|
| 22 |
+
}
|