TharunSivamani commited on
Commit
a08fc98
1 Parent(s): fc45a7c

tokenizer files

Browse files
tokenizer_files/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.32.0.dev0"
10
+ }
tokenizer_files/lit_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"name": "Llama-2-7b-chat-hf", "hf_config": {"org": "meta-llama", "name": "Llama-2-7b-chat-hf"}, "block_size": 4096, "vocab_size": 32000, "padding_multiple": 64, "padded_vocab_size": 32000, "n_layer": 32, "n_head": 32, "n_embd": 4096, "rotary_percentage": 1.0, "parallel_residual": false, "bias": false, "lm_head_bias": false, "n_query_groups": 32, "shared_attention_norm": false, "_norm_class": "RMSNorm", "norm_eps": 1e-05, "_mlp_class": "LLaMAMLP", "gelu_approximate": "none", "intermediate_size": 11008, "rope_condense_ratio": 1, "rope_base": 10000}
tokenizer_files/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_files/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_files/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
13
+ "clean_up_tokenization_spaces": false,
14
+ "eos_token": {
15
+ "__type": "AddedToken",
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "legacy": false,
23
+ "model_max_length": 1000000000000000019884624838656,
24
+ "pad_token": null,
25
+ "padding_side": "right",
26
+ "sp_model_kwargs": {},
27
+ "tokenizer_class": "LlamaTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }