ucalyptus commited on
Commit
1c1d1b6
1 Parent(s): 0f900e0

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Constant_2300_attr__value filter=lfs diff=lfs merge=lfs -text
37
+ Constant_2308_attr__value filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
Constant_2300_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d39d994a9f095ab7915db8b999513fda639b1c4c89d08dcd171269b9b8e7d15
3
+ size 2097152
Constant_2308_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a41b28fb845ff407014dea375801076b467e204937facf71c3803425ee087b9
3
+ size 2097152
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|end_header_id|>": 32001,
3
+ "<|eot_id|>": 32002,
4
+ "<|start_header_id|>": 32000,
5
+ "[PAD]": 32003
6
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "premai-io/prem-1B-chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.33.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32004
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d27432fc9919d0607f17a87840b231e7c81a8401c33a09962d3fe66416b0287
3
+ size 5254393
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea4bca99d48021a1811539418bcaef2a193461e7cdac61fbc385f69ffe6e49b
3
+ size 13199695872
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c178baa59144e6e1ec46001138a81af9650ff1f7bb73d0ee2d9c953956bb530a
3
+ size 1105728582
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9171b098983a8325152c9ed849be8fdab80fe7c406cb8ed6a980669b076a850d
3
+ size 1016507
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1ca70217cbd70e63fe2ae8272fc7fb91d88ec261c87a6fed83c03c083a2a08
3
+ size 4399898624
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc79f6ca338c88986b6ade19871087cfdd531c80448b959e9001762a43a3809
3
+ size 1101480490
quantize_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "ConstantOfShape",
8
+ "Mul",
9
+ "Transpose",
10
+ "Expand",
11
+ "Shape",
12
+ "Reshape",
13
+ "Slice",
14
+ "Cast",
15
+ "Neg",
16
+ "Concat",
17
+ "Unsqueeze",
18
+ "MatMul",
19
+ "Div",
20
+ "Constant",
21
+ "Gather",
22
+ "Less",
23
+ "Sqrt",
24
+ "Equal",
25
+ "Sub",
26
+ "Range",
27
+ "Sigmoid",
28
+ "Softmax",
29
+ "Pow",
30
+ "Add",
31
+ "Squeeze",
32
+ "ReduceMean",
33
+ "Where",
34
+ "Identity"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "model": {
39
+ "op_types": [
40
+ "ConstantOfShape",
41
+ "Mul",
42
+ "Transpose",
43
+ "Greater",
44
+ "ScatterND",
45
+ "Expand",
46
+ "Shape",
47
+ "Reshape",
48
+ "Slice",
49
+ "Cast",
50
+ "Neg",
51
+ "Concat",
52
+ "Unsqueeze",
53
+ "MatMul",
54
+ "Div",
55
+ "Constant",
56
+ "Cos",
57
+ "Gather",
58
+ "Sqrt",
59
+ "Trilu",
60
+ "And",
61
+ "Equal",
62
+ "Range",
63
+ "Sigmoid",
64
+ "Sin",
65
+ "Softmax",
66
+ "Pow",
67
+ "Add",
68
+ "ReduceMean",
69
+ "Where",
70
+ "Identity"
71
+ ],
72
+ "weight_type": "QInt8"
73
+ }
74
+ }
75
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_header_id|>",
4
+ "<|end_header_id|>",
5
+ "<|eot_id|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "[PAD]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<|start_header_id|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|end_header_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<|eot_id|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "[PAD]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<|start_header_id|>",
62
+ "<|end_header_id|>",
63
+ "<|eot_id|>"
64
+ ],
65
+ "bos_token": "<s>",
66
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
67
+ "clean_up_tokenization_spaces": false,
68
+ "eos_token": "</s>",
69
+ "legacy": false,
70
+ "model_max_length": 1000000000000000019884624838656,
71
+ "pad_token": "[PAD]",
72
+ "padding_side": "right",
73
+ "sp_model_kwargs": {},
74
+ "tokenizer_class": "LlamaTokenizer",
75
+ "unk_token": "<unk>",
76
+ "use_default_system_prompt": false
77
+ }