Initial Upload
Browse files# Llama-2-70B-Chat-GGUF-tokenizer-legacy
## Tokenizer for llama-2-70b-chat
This repository contains the following files: special_tokens_map.json, tokenizer_config.json, tokenizer.json, and tokenizer.model. These files are used to load a llama.cpp model as a HuggingFace Transformers model using [llamacpp_HF loader](https://github.com/oobabooga/text-generation-webui/blob/main/modules/llamacpp_hf.py).
Note: converted using [convert_llama_weights_to_hf.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py) with legacy method.
## How to use with [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui)
1. Download a .gguf file from [TheBloke/Llama-2-70B-Chat-GGUF](https://huggingface.co/TheBloke/Llama-2-70B-Chat-GGUF) based on your preferred quantization method;
2. Place your .gguf in a subfolder of models/ along with these 4 files.
- README.md +14 -3
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
@@ -1,3 +1,14 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Llama-2-70B-Chat-GGUF-tokenizer-legacy
|
2 |
+
|
3 |
+
## Tokenizer for llama-2-70b-chat
|
4 |
+
|
5 |
+
This repository contains the following files: special_tokens_map.json, tokenizer_config.json, tokenizer.json, and tokenizer.model. These files are used to load a llama.cpp model as a HuggingFace Transformers model using [llamacpp_HF loader](https://github.com/oobabooga/text-generation-webui/blob/main/modules/llamacpp_hf.py).
|
6 |
+
|
7 |
+
Note: converted using [convert_llama_weights_to_hf.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py) with legacy method.
|
8 |
+
|
9 |
+
## How to use with [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui)
|
10 |
+
|
11 |
+
1. Download a .gguf file from [TheBloke/Llama-2-70B-Chat-GGUF](https://huggingface.co/TheBloke/Llama-2-70B-Chat-GGUF) based on your preferred quantization method;
|
12 |
+
|
13 |
+
2. Place your .gguf in a subfolder of models/ along with these 4 files.
|
14 |
+
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
The diff for this file is too large to render.
See raw diff
|
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": null,
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"spaces_between_special_tokens": false,
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|