Delete tokenizer
Browse files- tokenizer/model.safetensors +0 -3
- tokenizer/save.py +0 -20
- tokenizer/special_tokens_map.json +0 -30
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer.model +0 -3
- tokenizer/tokenizer_config.json +0 -50
- tokenizer/upload.py +0 -26
tokenizer/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:da969d56fc3a8fcb72ae57f1484be0a65fc365b6374d98c2460c16a53dceda0a
|
3 |
-
size 4400216504
|
|
|
|
|
|
|
|
tokenizer/save.py
DELETED
@@ -1,20 +0,0 @@
|
|
1 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
2 |
-
import torch
|
3 |
-
from safetensors.torch import save_file
|
4 |
-
|
5 |
-
# Load your model and tokenizer
|
6 |
-
model_name = "Stefan171/TinyLlama-QuantumQuill-chat-12-05-24"
|
7 |
-
model = AutoModelForCausalLM.from_pretrained(model_name)
|
8 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
9 |
-
|
10 |
-
# Define the path to save the safetensors model in the current directory
|
11 |
-
safetensors_path = "./model.safetensors"
|
12 |
-
|
13 |
-
# Convert model parameters to a dictionary
|
14 |
-
state_dict = model.state_dict()
|
15 |
-
|
16 |
-
# Save the model parameters in safetensors format
|
17 |
-
save_file(state_dict, safetensors_path)
|
18 |
-
|
19 |
-
# Save the tokenizer in the current directory
|
20 |
-
tokenizer.save_pretrained("./")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/special_tokens_map.json
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/tokenizer.model
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
-
size 499723
|
|
|
|
|
|
|
|
tokenizer/tokenizer_config.json
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false,
|
27 |
-
"special": true
|
28 |
-
}
|
29 |
-
},
|
30 |
-
"additional_special_tokens": [],
|
31 |
-
"bos_token": "<s>",
|
32 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
-
"clean_up_tokenization_spaces": false,
|
34 |
-
"cls_token": null,
|
35 |
-
"eos_token": "</s>",
|
36 |
-
"mask_token": null,
|
37 |
-
"model_input_names": [
|
38 |
-
"input_ids",
|
39 |
-
"attention_mask"
|
40 |
-
],
|
41 |
-
"model_max_length": 16000,
|
42 |
-
"pad_token": "<unk>",
|
43 |
-
"padding_side": "left",
|
44 |
-
"sep_token": null,
|
45 |
-
"split_special_tokens": false,
|
46 |
-
"tokenizer_class": "LlamaTokenizer",
|
47 |
-
"truncation_side": "right",
|
48 |
-
"unk_token": "<unk>",
|
49 |
-
"use_default_system_prompt": false
|
50 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/upload.py
DELETED
@@ -1,26 +0,0 @@
|
|
1 |
-
from huggingface_hub import HfApi
|
2 |
-
|
3 |
-
api = HfApi()
|
4 |
-
model_id = "Stefan171/TinyLlama-QuantumQuill-chat-12-05-24"
|
5 |
-
|
6 |
-
# Path to the safetensors model file
|
7 |
-
safetensors_path = "./model.safetensors"
|
8 |
-
|
9 |
-
# Upload the safetensors model
|
10 |
-
api.upload_file(
|
11 |
-
path_or_fileobj=safetensors_path,
|
12 |
-
path_in_repo="model.safetensors",
|
13 |
-
repo_id=model_id,
|
14 |
-
repo_type="model"
|
15 |
-
)
|
16 |
-
|
17 |
-
# Path to the tokenizer folder (current directory)
|
18 |
-
tokenizer_path = "./"
|
19 |
-
|
20 |
-
# Upload the tokenizer files
|
21 |
-
api.upload_folder(
|
22 |
-
folder_path=tokenizer_path,
|
23 |
-
path_in_repo="tokenizer",
|
24 |
-
repo_id=model_id,
|
25 |
-
repo_type="model"
|
26 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|