Laziz HAMDI
commited on
Commit
•
7d080f8
1
Parent(s):
64e2277
adding files : generation_config.json, special_tokens_map.json, tokenizer.json, tokenizer_config.json
Browse files- config.json +32 -0
- generation_config.json +6 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +8 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alibi": false,
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"RWForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_RW.RWConfig",
|
10 |
+
"AutoModel": "modelling_RW.RWModel",
|
11 |
+
"AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
|
12 |
+
"AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification",
|
13 |
+
"AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
|
14 |
+
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
|
15 |
+
},
|
16 |
+
"bias": false,
|
17 |
+
"bos_token_id": 11,
|
18 |
+
"eos_token_id": 11,
|
19 |
+
"hidden_dropout": 0.0,
|
20 |
+
"hidden_size": 4544,
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"layer_norm_epsilon": 1e-05,
|
23 |
+
"model_type": "RefinedWebModel",
|
24 |
+
"multi_query": true,
|
25 |
+
"n_head": 71,
|
26 |
+
"n_layer": 32,
|
27 |
+
"parallel_attn": true,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.27.4",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 65024
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.27.4"
|
6 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
">>DOMAIN<<",
|
11 |
+
">>PREFIX<<",
|
12 |
+
">>SUFFIX<<",
|
13 |
+
">>MIDDLE<<"
|
14 |
+
],
|
15 |
+
"eos_token": "<|endoftext|>"
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"model_max_length": 2048,
|
5 |
+
"name_or_path": "tiiuae/falcon_tokenizer",
|
6 |
+
"special_tokens_map_file": null,
|
7 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
8 |
+
}
|