jeiku commited on
Commit
f00afda
1 Parent(s): 9494109

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.01,
17
+ "intermediate_size": 5888,
18
+ "max_length": 4096,
19
+ "max_position_embeddings": 4096,
20
+ "model_type": "index",
21
+ "norm_head": 1,
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 36,
24
+ "num_key_value_heads": 16,
25
+ "pad_token_id": 0,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.41.1",
33
+ "use_cache": false,
34
+ "vocab_size": 65029
35
+ }
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": "4.41.1"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8e3c935be74d4c1a9cfe27939ab1616f9f0138f68e66422e8afe97f38c1670
3
+ size 4612035624
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": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": true
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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
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": "<unk>",
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
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff