Upload folder using huggingface_hub
Browse files- config.json +36 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +66 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "IndexTeam/Index-1.9B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"IndexForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "IndexTeam/Index-1.9B-Chat--configuration_index.IndexConfig",
|
10 |
+
"AutoModelForCausalLM": "IndexTeam/Index-1.9B-Chat--modeling_index.IndexForCausalLM",
|
11 |
+
"AutoModelForSequenceClassification": "IndexTeam/Index-1.9B-Chat--modeling_index.IndexForSequenceClassification"
|
12 |
+
},
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 2048,
|
17 |
+
"initializer_range": 0.01,
|
18 |
+
"intermediate_size": 5888,
|
19 |
+
"max_length": 4096,
|
20 |
+
"max_position_embeddings": 4096,
|
21 |
+
"model_type": "index",
|
22 |
+
"norm_head": 1,
|
23 |
+
"num_attention_heads": 16,
|
24 |
+
"num_hidden_layers": 36,
|
25 |
+
"num_key_value_heads": 16,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"pretraining_tp": 1,
|
28 |
+
"rms_norm_eps": 1e-06,
|
29 |
+
"rope_scaling": null,
|
30 |
+
"rope_theta": 10000.0,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.42.3",
|
34 |
+
"use_cache": false,
|
35 |
+
"vocab_size": 65029
|
36 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"repetition_penalty": 1.1,
|
8 |
+
"temperature": 0.3,
|
9 |
+
"top_k": 5,
|
10 |
+
"top_p": 0.8,
|
11 |
+
"transformers_version": "4.42.3"
|
12 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf12e6a959461f86a64a3e85db1774f68f17d321a0dc3c64a33c6eda5844ec9e
|
3 |
+
size 4345676792
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "</s>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a11626b3c80cbfdd5f4b5585fce8938d178f3a0df739c3dd1c708ce944878af
|
3 |
+
size 1010047
|
tokenizer_config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "reserved_0",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "reserved_1",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"auto_map": {
|
48 |
+
"AutoTokenizer": [
|
49 |
+
"IndexTeam/Index-1.9B-Chat--tokenization_index.IndexTokenizer",
|
50 |
+
null
|
51 |
+
]
|
52 |
+
},
|
53 |
+
"bos_token": "<s>",
|
54 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ unk_token + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'reserved_0' + content.strip() + 'reserved_1' }}{% elif message['role'] == 'assistant' %}{{ content.strip() }}{% endif %}{% endfor %}",
|
55 |
+
"clean_up_tokenization_spaces": false,
|
56 |
+
"decode_with_prefix_space": false,
|
57 |
+
"eos_token": "</s>",
|
58 |
+
"legacy": false,
|
59 |
+
"model_max_length": 1e+30,
|
60 |
+
"pad_token": "</s>",
|
61 |
+
"sp_model_kwargs": {},
|
62 |
+
"spaces_between_special_tokens": false,
|
63 |
+
"tokenizer_class": "IndexTokenizer",
|
64 |
+
"unk_token": "<unk>",
|
65 |
+
"use_default_system_prompt": false
|
66 |
+
}
|