Hugging Face's logo

BricksDisplay
/
Mistral-7B-v0.1

Text Generation
Transformers
ONNX
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
hans00 commited on
Commit
b09b7ea
•
1 Parent(s): f598638

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +6 -0
  2. config.json +25 -0
  3. generation_config.json +6 -0
  4. onnx/decoder_model.onnx +3 -0
  5. onnx/decoder_model.onnx_data +3 -0
  6. onnx/decoder_model_merged.onnx +3 -0
  7. onnx/decoder_model_merged.onnx_data +3 -0
  8. onnx/decoder_model_merged_quantized.onnx +3 -0
  9. onnx/decoder_model_merged_quantized.onnx_data +3 -0
  10. onnx/decoder_model_quantized.onnx +3 -0
  11. onnx/decoder_model_quantized.onnx_data +3 -0
  12. onnx/decoder_with_past_model.onnx +3 -0
  13. onnx/decoder_with_past_model.onnx_data +3 -0
  14. onnx/decoder_with_past_model_quantized.onnx +3 -0
  15. onnx/decoder_with_past_model_quantized.onnx_data +3 -0
  16. quantize_config.json +101 -0
  17. special_tokens_map.json +23 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +42 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ 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
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/decoder_model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
41
+ onnx/decoder_with_past_model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "transformers_version": "4.39.3",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
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": "4.39.3"
6
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0feaacd963dd61052c5741836e6c3765a66cba731099d2acdb36068297fa6d5b
3
+ size 1558620
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7667087b4696b5ffb666cd6b390c4311dc5287b7739d071a047648cae7d1beee
3
+ size 29000482816
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d9c11a5766a488473549f91bec4d61de0d9750118fcf2b42d5b1714cba7f0c
3
+ size 3118406
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82b4f3e2ea7aed6094060325fc9ee2dbec25eb47703fd78f927c8cc029faa22
3
+ size 29034037248
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618c9e23119458ff3fb11dfa6223e186f79aa041fb10610931638b2ada6b3e27
3
+ size 4768802
onnx/decoder_model_merged_quantized.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac95e5a766601691a2be7a0a378e5b49a1f714bfc647c628014e2a606609c1cd
3
+ size 7309639680
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5fb2b8cfe774540e287af1025b251f770d5fa1bef207936b2b1c8059a6eaf8
3
+ size 2382957
onnx/decoder_model_quantized.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0c7af93e9457c75d7d2df5546f19d004b8c8ad3702cfe1192cc4cb00ec9b3c
3
+ size 7276085248
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2875373aa21844868a2cd21c5ca8a8d57f662f34c04d11bd690f19b7591aa20b
3
+ size 1580956
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7667087b4696b5ffb666cd6b390c4311dc5287b7739d071a047648cae7d1beee
3
+ size 29000482816
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377881e0df34aaf7d24d6306b67e4768676e14ce18038c696f2c96fff8ca9bda
3
+ size 2413002
onnx/decoder_with_past_model_quantized.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0c7af93e9457c75d7d2df5546f19d004b8c8ad3702cfe1192cc4cb00ec9b3c
3
+ size 7276085248
quantize_config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Gather",
8
+ "Reshape",
9
+ "ReduceMean",
10
+ "Mul",
11
+ "Sub",
12
+ "Unsqueeze",
13
+ "Where",
14
+ "Div",
15
+ "Transpose",
16
+ "Concat",
17
+ "Shape",
18
+ "Add",
19
+ "Squeeze",
20
+ "Equal",
21
+ "MatMul",
22
+ "Neg",
23
+ "Less",
24
+ "Softmax",
25
+ "Slice",
26
+ "ConstantOfShape",
27
+ "Pow",
28
+ "Sigmoid",
29
+ "Constant",
30
+ "Expand",
31
+ "Range",
32
+ "Cast",
33
+ "Sqrt"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "Gather",
40
+ "Reshape",
41
+ "ReduceMean",
42
+ "Mul",
43
+ "Sub",
44
+ "Unsqueeze",
45
+ "Where",
46
+ "Div",
47
+ "Transpose",
48
+ "If",
49
+ "Concat",
50
+ "Shape",
51
+ "Add",
52
+ "Squeeze",
53
+ "Equal",
54
+ "MatMul",
55
+ "Neg",
56
+ "Less",
57
+ "Softmax",
58
+ "Slice",
59
+ "ConstantOfShape",
60
+ "Pow",
61
+ "Sigmoid",
62
+ "Constant",
63
+ "Expand",
64
+ "Range",
65
+ "Cast",
66
+ "Sqrt"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "Gather",
73
+ "Reshape",
74
+ "ReduceMean",
75
+ "Mul",
76
+ "Sub",
77
+ "Unsqueeze",
78
+ "Where",
79
+ "Div",
80
+ "Transpose",
81
+ "Concat",
82
+ "Shape",
83
+ "Add",
84
+ "Equal",
85
+ "MatMul",
86
+ "Neg",
87
+ "Softmax",
88
+ "Slice",
89
+ "ConstantOfShape",
90
+ "Pow",
91
+ "Sigmoid",
92
+ "Constant",
93
+ "Expand",
94
+ "Range",
95
+ "Cast",
96
+ "Sqrt"
97
+ ],
98
+ "weight_type": "QInt8"
99
+ }
100
+ }
101
+ }
special_tokens_map.json ADDED
@@ -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
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }