vriveras commited on
Commit
9bae679
1 Parent(s): fdf56d9

Upload converted mistral model

Browse files
genai_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "model.onnx",
11
+ "head_size": 128,
12
+ "hidden_size": 4096,
13
+ "inputs": {
14
+ "input_ids": "input_ids",
15
+ "attention_mask": "attention_mask",
16
+ "position_ids": "position_ids",
17
+ "past_key_names": "past_key_values.%d.key",
18
+ "past_value_names": "past_key_values.%d.value"
19
+ },
20
+ "outputs": {
21
+ "logits": "logits",
22
+ "present_key_names": "present.%d.key",
23
+ "present_value_names": "present.%d.value"
24
+ },
25
+ "num_attention_heads": 32,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8
28
+ },
29
+ "eos_token_id": 2,
30
+ "pad_token_id": 2,
31
+ "type": "mistral",
32
+ "vocab_size": 32000
33
+ },
34
+ "search": {
35
+ "diversity_penalty": 0.0,
36
+ "do_sample": false,
37
+ "early_stopping": true,
38
+ "length_penalty": 1.0,
39
+ "max_length": 32768,
40
+ "min_length": 0,
41
+ "no_repeat_ngram_size": 0,
42
+ "num_beams": 1,
43
+ "num_return_sequences": 1,
44
+ "past_present_share_buffer": false,
45
+ "repetition_penalty": 1.0,
46
+ "temperature": 1.0,
47
+ "top_k": 1,
48
+ "top_p": 1.0
49
+ }
50
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2482bbaa0420a6f8b9907ce8a13c4c1f0a95b0ee7258cd2eebb62cf360cbb3
3
+ size 798022
model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbb68b7b38ed10455f0ee312e8c1a04fac3a677fa56e10cacf26e97017fbb97
3
+ size 4986126336
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_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
+ }