sayanbanerjee32
commited on
Upload folder using huggingface_hub
Browse files- config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +1 -1
- tokenizer.json +8 -1
- tokenizer_config.json +3 -0
config.json
CHANGED
@@ -32,5 +32,5 @@
|
|
32 |
"torch_dtype": "float16",
|
33 |
"transformers_version": "4.44.2",
|
34 |
"use_cache": true,
|
35 |
-
"vocab_size":
|
36 |
}
|
|
|
32 |
"torch_dtype": "float16",
|
33 |
"transformers_version": "4.44.2",
|
34 |
"use_cache": true,
|
35 |
+
"vocab_size": 32011
|
36 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e01f106f725831ac3c787a4a4d985605130f750df169e7283e3950777b03707
|
3 |
+
size 4972163568
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6ab18a2b30b806f0465852321a8b68bbd065eef2d6739bd73396b48f0dcb36a
|
3 |
+
size 2669366856
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 7641507840
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
tokenizer.json
CHANGED
@@ -1,7 +1,14 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": {
|
5 |
+
"strategy": "BatchLongest",
|
6 |
+
"direction": "Right",
|
7 |
+
"pad_to_multiple_of": null,
|
8 |
+
"pad_id": 32000,
|
9 |
+
"pad_type_id": 0,
|
10 |
+
"pad_token": "<|endoftext|>"
|
11 |
+
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -121,8 +121,11 @@
|
|
121 |
"clean_up_tokenization_spaces": false,
|
122 |
"eos_token": "<|endoftext|>",
|
123 |
"legacy": false,
|
|
|
124 |
"model_max_length": 4096,
|
|
|
125 |
"pad_token": "<|endoftext|>",
|
|
|
126 |
"padding_side": "right",
|
127 |
"sp_model_kwargs": {},
|
128 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
121 |
"clean_up_tokenization_spaces": false,
|
122 |
"eos_token": "<|endoftext|>",
|
123 |
"legacy": false,
|
124 |
+
"max_length": null,
|
125 |
"model_max_length": 4096,
|
126 |
+
"pad_to_multiple_of": null,
|
127 |
"pad_token": "<|endoftext|>",
|
128 |
+
"pad_token_type_id": 0,
|
129 |
"padding_side": "right",
|
130 |
"sp_model_kwargs": {},
|
131 |
"tokenizer_class": "LlamaTokenizer",
|