Update README.md
Browse files
README.md
CHANGED
@@ -34,7 +34,52 @@ pipeline_tag: text2text-generation
|
|
34 |
# Model Card for Evolutionary Multi-Modal Model
|
35 |
|
36 |
## Model Details
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
### Model Description
|
39 |
|
40 |
This model, named `Evolutionary Multi-Modal Model`, is a multimodal transformer designed to handle a variety of tasks including vision and audio processing. It is built on top of the `adapter-transformers` and `transformers` libraries and is intended to be a versatile base model for both direct use and fine-tuning.
|
|
|
34 |
# Model Card for Evolutionary Multi-Modal Model
|
35 |
|
36 |
## Model Details
|
37 |
+
model_name: Evolutionary Multi-Modal Model
|
38 |
+
model_type: transformer
|
39 |
+
license: mit
|
40 |
+
language: en zh
|
41 |
+
datasets:
|
42 |
+
- "Custom"
|
43 |
+
tags:
|
44 |
+
- text-generation
|
45 |
+
- code-generation
|
46 |
+
- speech-recognition
|
47 |
+
- multi-modal
|
48 |
+
- evolutionary
|
49 |
+
base_model: facebook/bart-base
|
50 |
+
finetuned_from: gpt2, bert-base-uncased, facebook/wav2vec2-base-960h, openai/clip-vit-base-patch32
|
51 |
+
dataset: Custom Multi-Modal Dataset
|
52 |
|
53 |
+
metrics:
|
54 |
+
- perplexity
|
55 |
+
- bleu
|
56 |
+
- wer
|
57 |
+
- cer
|
58 |
+
|
59 |
+
library_name: transformers
|
60 |
+
pipeline_tag: text-generation
|
61 |
+
inference:
|
62 |
+
parameters:
|
63 |
+
max_length: 50
|
64 |
+
top_k: 50
|
65 |
+
top_p: 0.95
|
66 |
+
temperature: 1.2
|
67 |
+
do_sample: true
|
68 |
+
|
69 |
+
speech_recognition:
|
70 |
+
waveform_path: "C:/Users/baby7/Desktop/权重参数/sample-15s.wav"
|
71 |
+
task: "speech_recognition"
|
72 |
+
output_audio_key: "Transcription"
|
73 |
+
|
74 |
+
text_generation:
|
75 |
+
input_text: "What is the future of AI?"
|
76 |
+
task: "text_generation"
|
77 |
+
output_text_key: "Generated Text"
|
78 |
+
|
79 |
+
code_generation:
|
80 |
+
input_code: "def add(a, b): return"
|
81 |
+
task: "code_generation"
|
82 |
+
output_code_key: "Generated Code"
|
83 |
### Model Description
|
84 |
|
85 |
This model, named `Evolutionary Multi-Modal Model`, is a multimodal transformer designed to handle a variety of tasks including vision and audio processing. It is built on top of the `adapter-transformers` and `transformers` libraries and is intended to be a versatile base model for both direct use and fine-tuning.
|