Update README.md
Browse files
README.md
CHANGED
@@ -1,33 +1,46 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
7 |
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
|
12 |
## Model Details
|
13 |
|
14 |
### Model Description
|
15 |
|
16 |
-
<!-- Provide a longer summary of what this model is. -->
|
17 |
-
|
18 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
|
20 |
-
- **Developed by:** [
|
21 |
- **Funded by [optional]:** [More Information Needed]
|
22 |
- **Shared by [optional]:** [More Information Needed]
|
23 |
-
- **Model type:** [
|
24 |
-
- **Language(s) (NLP):** [
|
25 |
-
- **License:** [
|
26 |
-
- **Finetuned from model
|
27 |
|
28 |
-
### Model Sources
|
29 |
-
|
30 |
-
<!-- Provide the basic links for the model. -->
|
31 |
|
32 |
- **Repository:** [More Information Needed]
|
33 |
- **Paper [optional]:** [More Information Needed]
|
@@ -35,51 +48,70 @@ This is the model card of a 🤗 transformers model that has been pushed on the
|
|
35 |
|
36 |
## Uses
|
37 |
|
38 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
-
|
40 |
### Direct Use
|
41 |
|
42 |
-
|
|
|
|
|
43 |
|
44 |
-
[More Information Needed]
|
45 |
|
46 |
### Downstream Use [optional]
|
47 |
|
48 |
-
|
|
|
|
|
49 |
|
50 |
-
[More Information Needed]
|
51 |
|
52 |
### Out-of-Scope Use
|
53 |
|
54 |
-
|
|
|
|
|
|
|
55 |
|
56 |
-
[More Information Needed]
|
57 |
|
58 |
## Bias, Risks, and Limitations
|
59 |
|
60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
-
[More Information Needed]
|
63 |
|
64 |
### Recommendations
|
65 |
|
66 |
-
|
|
|
67 |
|
68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
|
70 |
## How to Get Started with the Model
|
71 |
|
72 |
-
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
-
[More Information Needed]
|
75 |
|
76 |
## Training Details
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
-
|
|
|
|
|
|
|
|
|
|
|
81 |
|
82 |
-
[More Information Needed]
|
83 |
|
84 |
### Training Procedure
|
85 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- code
|
5 |
+
- bug-fix
|
6 |
+
- code-generation
|
7 |
+
- code-repair
|
8 |
+
- codet5p
|
9 |
+
- ai
|
10 |
+
- machine-learning
|
11 |
+
- deep-learning
|
12 |
+
- huggingface
|
13 |
+
- finetuned-model
|
14 |
+
license: apache-2.0
|
15 |
+
datasets:
|
16 |
+
- Girinath11/aiml_code_debug_dataset
|
17 |
+
metrics:
|
18 |
+
- bleu
|
19 |
+
base_model:
|
20 |
+
- Salesforce/codet5p-220m
|
21 |
---
|
22 |
|
23 |
# Model Card for Model ID
|
24 |
|
25 |
+
This is a fine-tuned version of the [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) model, specialized for real-world AI, ML, and Deep Learning code bug-fix tasks.
|
26 |
+
The model was trained on 150,000 code pairs (buggy → fixed) extracted from GitHub projects relevant to the AI/ML/GenAI ecosystem.
|
27 |
+
It is optimized for suggesting correct code fixes from faulty code snippets and is highly effective for debugging and auto-correction in AI coding environments.
|
28 |
|
29 |
## Model Details
|
30 |
|
31 |
### Model Description
|
32 |
|
|
|
|
|
33 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
34 |
|
35 |
+
- **Developed by:** [Girinath V]
|
36 |
- **Funded by [optional]:** [More Information Needed]
|
37 |
- **Shared by [optional]:** [More Information Needed]
|
38 |
+
- **Model type:** [Text-to-text Transformer (Encoder-Decoder)]
|
39 |
+
- **Language(s) (NLP):** [Programming (Python, some support for other AI/ML languages]
|
40 |
+
- **License:** [Apache 2.0]
|
41 |
+
- **Finetuned from model:** [[Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m)]
|
42 |
|
43 |
+
### Model Sources:
|
|
|
|
|
44 |
|
45 |
- **Repository:** [More Information Needed]
|
46 |
- **Paper [optional]:** [More Information Needed]
|
|
|
48 |
|
49 |
## Uses
|
50 |
|
|
|
|
|
51 |
### Direct Use
|
52 |
|
53 |
+
-Fix real-world AI/ML/GenAI Python code bugs.
|
54 |
+
- Debug model training scripts, data pipelines, and inference code.
|
55 |
+
- Educational use for learning from code correction.
|
56 |
|
|
|
57 |
|
58 |
### Downstream Use [optional]
|
59 |
|
60 |
+
- Integrated into code review pipelines.
|
61 |
+
- LLM-enhanced IDE plugins for auto-fixing AI-related bugs.
|
62 |
+
- Assistant agents in AI-powered coding copilots.
|
63 |
|
|
|
64 |
|
65 |
### Out-of-Scope Use
|
66 |
|
67 |
+
- General-purpose natural language tasks.
|
68 |
+
- Code generation unrelated to AI/ML domains.
|
69 |
+
- Use on production code without human review.
|
70 |
+
|
71 |
|
|
|
72 |
|
73 |
## Bias, Risks, and Limitations
|
74 |
|
75 |
+
## Biases
|
76 |
+
|
77 |
+
- Model favors AI/ML/GenAI-related Python patterns.
|
78 |
+
- Not trained for full-stack or UI/frontend code debugging.
|
79 |
+
|
80 |
+
### Limitations
|
81 |
+
|
82 |
+
- May not generalize well outside its fine-tuned domain.
|
83 |
+
- Struggles with ambiguous or undocumented buggy code.
|
84 |
+
|
85 |
+
|
86 |
|
|
|
87 |
|
88 |
### Recommendations
|
89 |
|
90 |
+
- Use alongside human review.
|
91 |
+
- Combine with static analysis for best results.
|
92 |
|
|
|
93 |
|
94 |
## How to Get Started with the Model
|
95 |
|
96 |
+
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
97 |
+
tokenizer = AutoTokenizer.from_pretrained("Girinath11/aiml_code_debug_model")
|
98 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("Girinath11/aiml_code_debug_model")
|
99 |
+
inputs = tokenizer("buggy: def add(a,b) return a+b", return_tensors="pt")
|
100 |
+
outputs = model.generate(**inputs)
|
101 |
+
print(tokenizer.decode(outputs[0]))
|
102 |
|
|
|
103 |
|
104 |
## Training Details
|
105 |
|
106 |
### Training Data
|
107 |
|
108 |
+
-150,000 real-world buggy–fixed Python code pairs.
|
109 |
+
|
110 |
+
-Data collected from GitHub AI/ML repositories.
|
111 |
+
|
112 |
+
-Includes data cleaning, formatting, deduplication.
|
113 |
+
|
114 |
|
|
|
115 |
|
116 |
### Training Procedure
|
117 |
|