Update README(2).md and add new files in hw-midm-7b-nsmc submodule
Browse files- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- midm_bitext_tokenizer.model +3 -0
- special_tokens_map(1).json +12 -0
- tokenizer_config(1).json +52 -0
- training_args(1).bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "KT-AI/midm-bitext-S-7B-inst-v1",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"c_proj",
|
23 |
+
"c_fc",
|
24 |
+
"c_attn"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM"
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55184b373b2c621386f35c6d2df598cf1f852b4103a1e67b145c2768b544c0aa
|
3 |
+
size 67010784
|
midm_bitext_tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98789fa1bf89a1f9692889fb4a0029d3d096a9109cebf4f6bce1a255f2701378
|
3 |
+
size 1457356
|
special_tokens_map(1).json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
tokenizer_config(1).json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "</s>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"additional_special_tokens": [],
|
37 |
+
"auto_map": {
|
38 |
+
"AutoTokenizer": [
|
39 |
+
"KT-AI/midm-bitext-S-7B-inst-v1--midm_bitext_tokenization.Midm_bitext_Tokenizer",
|
40 |
+
null
|
41 |
+
]
|
42 |
+
},
|
43 |
+
"bos_token": "<s>",
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"eos_token": "</s>",
|
46 |
+
"extra_ids": 0,
|
47 |
+
"model_max_length": 1000000000000000019884624838656,
|
48 |
+
"pad_token": "<pad>",
|
49 |
+
"sp_model_kwargs": {},
|
50 |
+
"tokenizer_class": "Midm_bitext_Tokenizer",
|
51 |
+
"unk_token": "<unk>"
|
52 |
+
}
|
training_args(1).bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b83130d9f853efa920b3341c44aec5292cffd4227bb6567b63a0f68322ee33f1
|
3 |
+
size 4600
|