Ian Walton
commited on
Commit
•
29f4fd5
1
Parent(s):
541d020
Add tokenizer and model config.
Browse files- config.json +20 -0
- generation_config.json +6 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RwkvForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_hidden_size": 2048,
|
6 |
+
"bos_token_id": 2,
|
7 |
+
"context_length": 1024,
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"intermediate_size": 8192,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "rwkv",
|
13 |
+
"num_hidden_layers": 24,
|
14 |
+
"rescale_every": 6,
|
15 |
+
"tie_word_embeddings": false,
|
16 |
+
"torch_dtype": "float32",
|
17 |
+
"transformers_version": "4.29.0.dev0",
|
18 |
+
"use_cache": true,
|
19 |
+
"vocab_size": 50277
|
20 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.29.0.dev0"
|
6 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
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": 1000000000000000019884624838656,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|