Julius ter Pelkwijk
commited on
Commit
·
dfc3204
1
Parent(s):
07804a9
Adding model
Browse files- config.json +29 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KoboldAI/fairseq-dense-13B",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"XGLMForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"attention_heads": 40,
|
10 |
+
"bos_token_id": 50257,
|
11 |
+
"d_model": 5120,
|
12 |
+
"decoder_start_token_id": 2,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"eos_token_id": 50259,
|
15 |
+
"ffn_dim": 20480,
|
16 |
+
"init_std": 0.02,
|
17 |
+
"layerdrop": 0.0,
|
18 |
+
"max_position_embeddings": 2048,
|
19 |
+
"model_type": "xglm",
|
20 |
+
"newlinemode": "s",
|
21 |
+
"num_layers": 40,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"scale_embedding": true,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.18.0",
|
27 |
+
"use_cache": false,
|
28 |
+
"vocab_size": 50261
|
29 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf2c054115933e90334ecabf9f805a8f7cc99583becc10b8e6d2c3740c147a13
|
3 |
+
size 25707041085
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<|endoftext|>", "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "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, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d62d75cc3a7250ada25f0a99e2741555d3712693661d5eef48b3fcbdd151d255.f4b0476f9d35aab16d5dd877dd9e5d547702eff96a3d808497c0d3fc36a32c99", "name_or_path": "KoboldAI/fairseq-dense-13B", "tokenizer_class": "GPT2Tokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|