Commit
·
680e007
1
Parent(s):
f34c08a
Upload 4 files
Browse files- config.json +2 -5
- special_tokens_map.json +2 -8
- tokenizer.json +0 -0
- tokenizer_config.json +6 -3
config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "EleutherAI/pythia-19m",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -10,7 +9,6 @@
|
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 2048,
|
12 |
"layer_norm_eps": 1e-05,
|
13 |
-
"line_by_line": true,
|
14 |
"max_position_embeddings": 2048,
|
15 |
"model_type": "gpt_neox",
|
16 |
"num_attention_heads": 8,
|
@@ -18,9 +16,8 @@
|
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 0.25,
|
20 |
"tie_word_embeddings": false,
|
21 |
-
"torch_dtype": "
|
22 |
-
"transformers_version": "4.
|
23 |
"use_cache": true,
|
24 |
-
"use_parallel_residual": true,
|
25 |
"vocab_size": 50304
|
26 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"GPTNeoXForCausalLM"
|
4 |
],
|
|
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 2048,
|
11 |
"layer_norm_eps": 1e-05,
|
|
|
12 |
"max_position_embeddings": 2048,
|
13 |
"model_type": "gpt_neox",
|
14 |
"num_attention_heads": 8,
|
|
|
16 |
"rotary_emb_base": 10000,
|
17 |
"rotary_pct": 0.25,
|
18 |
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.22.2",
|
21 |
"use_cache": true,
|
|
|
22 |
"vocab_size": 50304
|
23 |
}
|
special_tokens_map.json
CHANGED
@@ -1,11 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"<|endoftext|>",
|
4 |
-
"<|sep|>",
|
5 |
-
"<|acc|>",
|
6 |
-
"<|tel|>",
|
7 |
-
"<|rrn|>"
|
8 |
-
],
|
9 |
"eos_token": "<|endoftext|>",
|
10 |
-
"
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
-
"
|
5 |
-
"
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
"eos_token": "<|endoftext|>",
|
5 |
+
"name_or_path": "EleutherAI/gpt-neox-20b",
|
6 |
+
"special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
}
|