Upload 8 files
Browse files- ct2fast-flan-alpaca-xxl/.gitattributes +34 -0
- ct2fast-flan-alpaca-xxl/README.md +38 -0
- ct2fast-flan-alpaca-xxl/config.json +8 -0
- ct2fast-flan-alpaca-xxl/model.bin +3 -0
- ct2fast-flan-alpaca-xxl/model.binZone.Identifier +4 -0
- ct2fast-flan-alpaca-xxl/shared_vocabulary.txt +0 -0
- ct2fast-flan-alpaca-xxl/tokenizer.json +0 -0
- ct2fast-flan-alpaca-xxl/tokenizer_config.json +112 -0
ct2fast-flan-alpaca-xxl/.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
ct2fast-flan-alpaca-xxl/README.md
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
---
|
4 |
+
# Fast-Inference with Ctranslate2
|
5 |
+
Speedup inference by 2x-8x using int8 inference in C++
|
6 |
+
|
7 |
+
quantized version of [declare-lab/flan-alpaca-xxl](https://huggingface.co/declare-lab/flan-alpaca-xxl)
|
8 |
+
```bash
|
9 |
+
pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0
|
10 |
+
```
|
11 |
+
|
12 |
+
|
13 |
+
Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
|
14 |
+
- `compute_type=int8_float16` for `device="cuda"`
|
15 |
+
- `compute_type=int8` for `device="cpu"`
|
16 |
+
|
17 |
+
```python
|
18 |
+
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
|
19 |
+
|
20 |
+
model_name = "michaelfeil/ct2fast-flan-alpaca-xxl"
|
21 |
+
model = TranslatorCT2fromHfHub(
|
22 |
+
# load in int8 on CUDA
|
23 |
+
model_name_or_path=model_name,
|
24 |
+
device="cuda",
|
25 |
+
compute_type="int8_float16"
|
26 |
+
)
|
27 |
+
outputs = model.generate(
|
28 |
+
text=["How do you call a fast Flan-ingo?", "Translate to german: How are you doing?"],
|
29 |
+
min_decoding_length=24,
|
30 |
+
max_decoding_length=32,
|
31 |
+
max_input_length=512,
|
32 |
+
beam_size=5
|
33 |
+
)
|
34 |
+
print(outputs)
|
35 |
+
```
|
36 |
+
|
37 |
+
# Licence and other remarks:
|
38 |
+
This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.
|
ct2fast-flan-alpaca-xxl/config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_source_bos": false,
|
3 |
+
"add_source_eos": false,
|
4 |
+
"bos_token": "<pad>",
|
5 |
+
"decoder_start_token": "<pad>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"unk_token": "<unk>"
|
8 |
+
}
|
ct2fast-flan-alpaca-xxl/model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35c0fd62b8f7b49175264ca887ade36a77587b86fb40ea23bb372fd7c20e4ed9
|
3 |
+
size 11145587784
|
ct2fast-flan-alpaca-xxl/model.binZone.Identifier
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[ZoneTransfer]
|
2 |
+
ZoneId=3
|
3 |
+
ReferrerUrl=https://huggingface.co/
|
4 |
+
HostUrl=https://cdn-lfs.huggingface.co/repos/0c/e1/0ce18c05aa8fb558cfacca62a2d6625c9eb548ec37d26f2cfaa611e3bf1d1c5b/35c0fd62b8f7b49175264ca887ade36a77587b86fb40ea23bb372fd7c20e4ed9?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27model.bin%3B+filename%3D%22model.bin%22%3B&response-content-type=application%2Foctet-stream&Expires=1686601840&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zLzBjL2UxLzBjZTE4YzA1YWE4ZmI1NThjZmFjY2E2MmEyZDY2MjVjOWViNTQ4ZWMzN2QyNmYyY2ZhYTYxMWUzYmYxZDFjNWIvMzVjMGZkNjJiOGY3YjQ5MTc1MjY0Y2E4ODdhZGUzNmE3NzU4N2I4NmZiNDBlYTIzYmIzNzJmZDdjMjBlNGVkOT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2ODY2MDE4NDB9fX1dfQ__&Signature=QG7QwbKOOe-4aiyQP1tzsZ2rEcmkls8%7EYrccmU5GNJ3Coc1%7ERzfmAvpjUiuFCqNrmEQaBgE8iVwlMW8xmc%7ExViykk9Xcd8riioauLemZ4X792KTeT8tAeraCpWIvqxhW%7E6PIX-eMBEDJfi38b8eD7cINlY71FruKrATpVFlrOXQOKbpkT2KETNop4efmGlmF11MDh5r31yYP-jAsG8P71dfsYSGGLk2bJqOea07RBG0O6DpRojnLfEvbxe8yN65XzEhygJ9ffehjRqlDTmD8F67eWzyZUpvEl69869JMbLkfy7EdPiYfROAH4R%7EMhdYzK6NyzoOVj18ErX83MEEobg__&Key-Pair-Id=KVTP0A1DKRTAX
|
ct2fast-flan-alpaca-xxl/shared_vocabulary.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ct2fast-flan-alpaca-xxl/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ct2fast-flan-alpaca-xxl/tokenizer_config.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"extra_ids": 100,
|
106 |
+
"model_max_length": 512,
|
107 |
+
"pad_token": "<pad>",
|
108 |
+
"sp_model_kwargs": {},
|
109 |
+
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
|
110 |
+
"tokenizer_class": "T5Tokenizer",
|
111 |
+
"unk_token": "<unk>"
|
112 |
+
}
|