Update README.md
Browse files
README.md
CHANGED
@@ -1,18 +1,22 @@
|
|
1 |
# Cheapity3 π·
|
2 |
-
|
|
|
3 |
|
4 |
## Motivation
|
|
|
5 |
- GPT models are expensive run.
|
6 |
- GPT models are monolingual.
|
7 |
|
8 |
## Solution
|
9 |
-
|
|
|
10 |
- Plus, they are cheaper to run.
|
11 |
|
12 |
-
I fine-tuned T5 on multiple languages (π¬π§ English, π©πͺ German, π«π· French) and multiple academic text snippets from
|
13 |
-
domains like tech, law, finance and science etc. to generate text, just like GPT models do.
|
14 |
|
15 |
## Usage
|
|
|
16 |
- Provide some text e.g `"Italy, officially the Italian Republic is a country consisting of"`
|
17 |
- Tell Cheapity3 how many words you want to generate e.g `15` -- π Yes, you can control the length.
|
18 |
- Cheapity3 reads your text and generates a continuation containing approximately 15 words.
|
@@ -24,31 +28,33 @@ tokenizer = AutoTokenizer.from_pretrained("flexudy/cheapity3")
|
|
24 |
|
25 |
model = AutoModelWithLMHead.from_pretrained("flexudy/cheapity3")
|
26 |
|
27 |
-
input_text = "
|
|
|
|
|
28 |
|
29 |
-
inputs = tokenizer
|
30 |
|
31 |
input_ids = inputs["input_ids"]
|
32 |
|
33 |
attention_mask = inputs["attention_mask"]
|
34 |
|
35 |
outputs = model.generate(
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
|
45 |
for i in range(4):
|
46 |
print(tokenizer.decode(outputs[i], skip_special_tokens=True, clean_up_tokenization_spaces=True))
|
47 |
|
48 |
-
#
|
49 |
-
# >
|
50 |
-
#
|
51 |
-
#
|
52 |
-
|
53 |
-
|
54 |
-
|
|
|
1 |
# Cheapity3 π·
|
2 |
+
|
3 |
+
GPT3-like T5 model trained to generate text in multiple languages.
|
4 |
|
5 |
## Motivation
|
6 |
+
|
7 |
- GPT models are expensive run.
|
8 |
- GPT models are monolingual.
|
9 |
|
10 |
## Solution
|
11 |
+
|
12 |
+
- Maybe, Small Models aren't Terrible (*SMarT*)
|
13 |
- Plus, they are cheaper to run.
|
14 |
|
15 |
+
I fine-tuned T5 on multiple languages (π¬π§ English, π©πͺ German, π«π· French) and multiple academic text snippets from
|
16 |
+
various domains like tech, law, finance and science etc. to generate text, just like GPT models do.
|
17 |
|
18 |
## Usage
|
19 |
+
|
20 |
- Provide some text e.g `"Italy, officially the Italian Republic is a country consisting of"`
|
21 |
- Tell Cheapity3 how many words you want to generate e.g `15` -- π Yes, you can control the length.
|
22 |
- Cheapity3 reads your text and generates a continuation containing approximately 15 words.
|
|
|
28 |
|
29 |
model = AutoModelWithLMHead.from_pretrained("flexudy/cheapity3")
|
30 |
|
31 |
+
input_text = """The mechanical engineering field requires an understanding of core areas including mechanics, dynamics,
|
32 |
+
thermodynamics, materials science, structural analysis, and
|
33 |
+
electricity. { _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ }""" # 15 words
|
34 |
|
35 |
+
inputs = tokenizer(input_text, return_tensors="pt", truncation=True, max_length=512)
|
36 |
|
37 |
input_ids = inputs["input_ids"]
|
38 |
|
39 |
attention_mask = inputs["attention_mask"]
|
40 |
|
41 |
outputs = model.generate(
|
42 |
+
input_ids=input_ids,
|
43 |
+
attention_mask=attention_mask,
|
44 |
+
max_length=128,
|
45 |
+
do_sample=True,
|
46 |
+
early_stopping=True,
|
47 |
+
num_return_sequences=4,
|
48 |
+
repetition_penalty=2.5
|
49 |
+
)
|
50 |
|
51 |
for i in range(4):
|
52 |
print(tokenizer.decode(outputs[i], skip_special_tokens=True, clean_up_tokenization_spaces=True))
|
53 |
|
54 |
+
# Italy, officially the Italian Republic is a country consisting of
|
55 |
+
# > Cheapity3 continuing:
|
56 |
+
# ... Developing the knowledge base for these core areas will enable engineers to build their capabilities rapidly and efficiently. ...
|
57 |
+
# ... The field of mechanics offers a variety and broad range for applications throughout the engineering/technological fields. ...
|
58 |
+
# ... Mechanics generally is not understood by students. While they can be employed in the field, mechanical engineering ...
|
59 |
+
# ... Introduction to mechanical engineering and core fields including chemical products, materials science, structural analysis, and geomatics ...
|
60 |
+
```
|