Upload 6 files
Browse filesAn INT4 quantized version of Llama-2-13b-chat-hf
- .gitattributes +1 -0
- genai_config.json +54 -0
- model.onnx +3 -0
- model.onnx.data +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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
|
genai_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": {
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"context_length": 4096,
|
5 |
+
"decoder": {
|
6 |
+
"session_options": {
|
7 |
+
"log_id": "onnxruntime-genai",
|
8 |
+
"provider_options": [
|
9 |
+
{
|
10 |
+
"dml": {}
|
11 |
+
}
|
12 |
+
]
|
13 |
+
},
|
14 |
+
"filename": "model.onnx",
|
15 |
+
"head_size": 128,
|
16 |
+
"hidden_size": 5120,
|
17 |
+
"inputs": {
|
18 |
+
"input_ids": "input_ids",
|
19 |
+
"attention_mask": "attention_mask",
|
20 |
+
"position_ids": "position_ids",
|
21 |
+
"past_key_names": "past_key_values.%d.key",
|
22 |
+
"past_value_names": "past_key_values.%d.value"
|
23 |
+
},
|
24 |
+
"outputs": {
|
25 |
+
"logits": "logits",
|
26 |
+
"present_key_names": "present.%d.key",
|
27 |
+
"present_value_names": "present.%d.value"
|
28 |
+
},
|
29 |
+
"num_attention_heads": 40,
|
30 |
+
"num_hidden_layers": 40,
|
31 |
+
"num_key_value_heads": 40
|
32 |
+
},
|
33 |
+
"eos_token_id": 2,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"type": "llama",
|
36 |
+
"vocab_size": 32000
|
37 |
+
},
|
38 |
+
"search": {
|
39 |
+
"diversity_penalty": 0.0,
|
40 |
+
"do_sample": true,
|
41 |
+
"early_stopping": true,
|
42 |
+
"length_penalty": 1.0,
|
43 |
+
"max_length": 4096,
|
44 |
+
"min_length": 0,
|
45 |
+
"no_repeat_ngram_size": 0,
|
46 |
+
"num_beams": 1,
|
47 |
+
"num_return_sequences": 1,
|
48 |
+
"past_present_share_buffer": true,
|
49 |
+
"repetition_penalty": 1.0,
|
50 |
+
"temperature": 0.6,
|
51 |
+
"top_k": 1,
|
52 |
+
"top_p": 0.9
|
53 |
+
}
|
54 |
+
}
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72e9189e3b8d77602943d82413ad7a106d1ef21d929a59dfe33cb55daf273f27
|
3 |
+
size 343788
|
model.onnx.data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca6950764c48bfd31e8d911f7857bec3802f8b845b50bec1e3b7240a7312ff69
|
3 |
+
size 7558588416
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|