Hugging Face's logo

microsoft
/
mistral-7b-instruct-v0.2-ONNX

Text Generation
Transformers
ONNX
ONNX
DML
ONNXRuntime
mistral
conversational
custom_code
Model card Files Community
2
parinitarahi commited on
Commit
6d52410
•
1 Parent(s): 4b8a4dd

Upload 14 files

Browse files
Files changed (14) hide show
  1. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/genai_config.json +49 -0
  2. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx +3 -0
  3. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx.data +3 -0
  4. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/special_tokens_map.json +23 -0
  5. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer.json +0 -0
  6. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer.model +3 -0
  7. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json +43 -0
  8. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/genai_config.json +49 -0
  9. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32.onnx +3 -0
  10. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32.onnx.data +3 -0
  11. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/special_tokens_map.json +23 -0
  12. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer.json +0 -0
  13. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer.model +3 -0
  14. onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer_config.json +43 -0
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/genai_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 32768,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": []
9
+ },
10
+ "filename": "mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx",
11
+ "head_size": 128,
12
+ "hidden_size": 4096,
13
+ "inputs": {
14
+ "input_ids": "input_ids",
15
+ "attention_mask": "attention_mask",
16
+ "past_key_names": "past_key_values.%d.key",
17
+ "past_value_names": "past_key_values.%d.value"
18
+ },
19
+ "outputs": {
20
+ "logits": "logits",
21
+ "present_key_names": "present.%d.key",
22
+ "present_value_names": "present.%d.value"
23
+ },
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 8
27
+ },
28
+ "eos_token_id": 2,
29
+ "pad_token_id": 2,
30
+ "type": "mistral",
31
+ "vocab_size": 32000
32
+ },
33
+ "search": {
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": true,
37
+ "length_penalty": 1.0,
38
+ "max_length": 32768,
39
+ "min_length": 0,
40
+ "no_repeat_ngram_size": 0,
41
+ "num_beams": 1,
42
+ "num_return_sequences": 1,
43
+ "past_present_share_buffer": true,
44
+ "repetition_penalty": 1.0,
45
+ "temperature": 1.0,
46
+ "top_k": 1,
47
+ "top_p": 1.0
48
+ }
49
+ }
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60342073f94d4ce822e4b0fd37e644fdd6e5c98ff87db4960630acf9bba6812
3
+ size 232817
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207f9a1ee9cb0df1e142e67b9647f317b57508816bf951c93367a7cabceac57d
3
+ size 4986126336
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/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
+ }
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/genai_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": {
3
+ "bos_token_id": 1,
4
+ "context_length": 32768,
5
+ "decoder": {
6
+ "session_options": {
7
+ "log_id": "onnxruntime-genai",
8
+ "provider_options": []
9
+ },
10
+ "filename": "mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32.onnx",
11
+ "head_size": 128,
12
+ "hidden_size": 4096,
13
+ "inputs": {
14
+ "input_ids": "input_ids",
15
+ "attention_mask": "attention_mask",
16
+ "past_key_names": "past_key_values.%d.key",
17
+ "past_value_names": "past_key_values.%d.value"
18
+ },
19
+ "outputs": {
20
+ "logits": "logits",
21
+ "present_key_names": "present.%d.key",
22
+ "present_value_names": "present.%d.value"
23
+ },
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 8
27
+ },
28
+ "eos_token_id": 2,
29
+ "pad_token_id": 2,
30
+ "type": "mistral",
31
+ "vocab_size": 32000
32
+ },
33
+ "search": {
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": true,
37
+ "length_penalty": 1.0,
38
+ "max_length": 32768,
39
+ "min_length": 0,
40
+ "no_repeat_ngram_size": 0,
41
+ "num_beams": 1,
42
+ "num_return_sequences": 1,
43
+ "past_present_share_buffer": true,
44
+ "repetition_penalty": 1.0,
45
+ "temperature": 1.0,
46
+ "top_k": 1,
47
+ "top_p": 1.0
48
+ }
49
+ }
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88fedcf87182a77107e58a0089c85b9531161c1ebee1e341e2a5ab8b1908035f
3
+ size 224434
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207f9a1ee9cb0df1e142e67b9647f317b57508816bf951c93367a7cabceac57d
3
+ size 4986126336
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/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
+ }
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }