sabre-code
commited on
Upload 6 files
Browse files- .gitattributes +2 -0
- genai_config.json +49 -0
- model.onnx +3 -0
- model.onnx.data +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer_config.json +50 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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 |
+
model.onnx.data filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
genai_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": {
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"context_length": 8192,
|
5 |
+
"decoder": {
|
6 |
+
"session_options": {
|
7 |
+
"log_id": "onnxruntime-genai",
|
8 |
+
"provider_options": []
|
9 |
+
},
|
10 |
+
"filename": "model.onnx",
|
11 |
+
"head_size": 256,
|
12 |
+
"hidden_size": 3072,
|
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": 16,
|
25 |
+
"num_hidden_layers": 28,
|
26 |
+
"num_key_value_heads": 16
|
27 |
+
},
|
28 |
+
"eos_token_id": 1,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"type": "gemma",
|
31 |
+
"vocab_size": 256000
|
32 |
+
},
|
33 |
+
"search": {
|
34 |
+
"diversity_penalty": 0.0,
|
35 |
+
"do_sample": false,
|
36 |
+
"early_stopping": true,
|
37 |
+
"length_penalty": 1.0,
|
38 |
+
"max_length": 8192,
|
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 |
+
}
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef9c7a753bf75e1a80394b7da3069925c4ce1e758c517fa47367a65565ba8317
|
3 |
+
size 176153
|
model.onnx.data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe6804ebac9e413bf67a4cb7a1df54f8dd307f1a3207dc1220cd992903896535
|
3 |
+
size 8490758144
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4db21bfaffa1fd75fd741df2d95dc51e539d5cc38b07934bae0d7d129db90662
|
3 |
+
size 17477581
|
tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<bos>",
|
39 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<eos>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
40 |
+
"clean_up_tokenization_spaces": false,
|
41 |
+
"eos_token": "<eos>",
|
42 |
+
"legacy": null,
|
43 |
+
"model_max_length": 1000000000000000019884624838656,
|
44 |
+
"pad_token": "<pad>",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"tokenizer_class": "GemmaTokenizer",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": false
|
50 |
+
}
|