Update README.md
Browse files
README.md
CHANGED
@@ -9,36 +9,24 @@ tags:
|
|
9 |
- medical
|
10 |
---
|
11 |
|
12 |
-
|
13 |
-
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
14 |
-
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
15 |
-
{{ card_data }}
|
16 |
-
---
|
17 |
-
|
18 |
-
# Model Card for {{ model_id | default("Model ID", true) }}
|
19 |
|
20 |
This is a medical fine tuned model from the [Falcon-7b-Instruction](https://huggingface.co/tiiuae/falcon-7b-instruct) Base using 500 steps & 6 epochs with [MedAware](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset) Dataset from [keivalya](https://huggingface.co/datasets/keivalya)
|
21 |
-
|
22 |
|
23 |
## Model Details
|
24 |
|
25 |
### Model Description
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
- **
|
32 |
-
- **
|
33 |
-
-
|
34 |
-
- **Language(s) (NLP):** {{ language | default("[More Information Needed]", true)}}
|
35 |
-
- **License:** {{ license | default("[More Information Needed]", true)}}
|
36 |
-
- **Finetuned from model [optional]:** {{ finetuned_from | default("[tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct)", true)}}
|
37 |
-
|
38 |
### Model Sources [optional]
|
39 |
|
40 |
-
<!-- Provide the basic links for the model. -->
|
41 |
-
|
42 |
- **Repository:** https://github.com/Josephrp/AI-challenge-hackathon/blob/master/falcon_7b_instruct_GaiaMiniMed_dataset.ipynb
|
43 |
- **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
|
44 |
|
@@ -54,7 +42,7 @@ This model should perform better at medical QnA tasks in a conversational manner
|
|
54 |
|
55 |
It is our hope that it will help improve patient outcomes and public health.
|
56 |
|
57 |
-
### Downstream Use
|
58 |
|
59 |
Use this model next to others and have group conversations to produce diagnoses , public health advisory , and personal hygene improvements.
|
60 |
|
@@ -78,7 +66,6 @@ Use the code below to get started with the model.
|
|
78 |
|
79 |
### Results
|
80 |
|
81 |
-
{{ results | default("[
|
82 |
|
83 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62a3bb1cd0d8c2c2169f0b88/F8GfMSJcAaH7pXvpUK_r3.png)
|
84 |
|
@@ -87,31 +74,34 @@ Use the code below to get started with the model.
|
|
87 |
TrainOutput(global_step=6150, training_loss=1.0597990553941183,
|
88 |
{'epoch': 6.0})
|
89 |
```
|
90 |
-
]", true)}}
|
91 |
|
92 |
|
93 |
### Training Data
|
94 |
|
95 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
96 |
|
97 |
{{ training_data | default("
|
98 |
```json
|
|
|
99 |
DatasetDict({
|
100 |
train: Dataset({
|
101 |
features: ['qtype', 'Question', 'Answer'],
|
102 |
num_rows: 16407
|
103 |
})
|
104 |
})
|
|
|
105 |
```
|
106 |
-
|
107 |
|
108 |
### Training Procedure
|
109 |
|
110 |
|
111 |
#### Preprocessing [optional]
|
112 |
|
113 |
-
|
|
|
|
|
114 |
|
|
|
115 |
|
116 |
#### Training Hyperparameters
|
117 |
|
@@ -119,10 +109,11 @@ DatasetDict({
|
|
119 |
|
120 |
#### Speeds, Sizes, Times [optional]
|
121 |
|
122 |
-
```
|
123 |
|
124 |
metrics={'train_runtime': 30766.4612, 'train_samples_per_second': 3.2, 'train_steps_per_second': 0.2,
|
125 |
'total_flos': 1.1252790565109983e+18, 'train_loss': 1.0597990553941183,", true)}}
|
|
|
126 |
```
|
127 |
|
128 |
## Environmental Impact
|
|
|
9 |
- medical
|
10 |
---
|
11 |
|
12 |
+
# Model Card for GaiaMiniMed
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
This is a medical fine tuned model from the [Falcon-7b-Instruction](https://huggingface.co/tiiuae/falcon-7b-instruct) Base using 500 steps & 6 epochs with [MedAware](https://huggingface.co/datasets/keivalya/MedQuad-MedicalQnADataset) Dataset from [keivalya](https://huggingface.co/datasets/keivalya)
|
15 |
+
|
16 |
|
17 |
## Model Details
|
18 |
|
19 |
### Model Description
|
20 |
|
21 |
+
- **Developed by:** [Tonic](https://www.huggingface.co/tonic)
|
22 |
+
- **Shared by :** [Tonic](https://www.huggingface.co/tonic)
|
23 |
+
- **Model type:** Medical Fine-Tuned Conversational Falcon 7b (Instruct)
|
24 |
+
- **Language(s) (NLP):** English
|
25 |
+
- **License:** MIT
|
26 |
+
- **Finetuned from model:**[tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct)
|
27 |
+
-
|
|
|
|
|
|
|
|
|
28 |
### Model Sources [optional]
|
29 |
|
|
|
|
|
30 |
- **Repository:** https://github.com/Josephrp/AI-challenge-hackathon/blob/master/falcon_7b_instruct_GaiaMiniMed_dataset.ipynb
|
31 |
- **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
|
32 |
|
|
|
42 |
|
43 |
It is our hope that it will help improve patient outcomes and public health.
|
44 |
|
45 |
+
### Downstream Use
|
46 |
|
47 |
Use this model next to others and have group conversations to produce diagnoses , public health advisory , and personal hygene improvements.
|
48 |
|
|
|
66 |
|
67 |
### Results
|
68 |
|
|
|
69 |
|
70 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/62a3bb1cd0d8c2c2169f0b88/F8GfMSJcAaH7pXvpUK_r3.png)
|
71 |
|
|
|
74 |
TrainOutput(global_step=6150, training_loss=1.0597990553941183,
|
75 |
{'epoch': 6.0})
|
76 |
```
|
|
|
77 |
|
78 |
|
79 |
### Training Data
|
80 |
|
|
|
81 |
|
82 |
{{ training_data | default("
|
83 |
```json
|
84 |
+
|
85 |
DatasetDict({
|
86 |
train: Dataset({
|
87 |
features: ['qtype', 'Question', 'Answer'],
|
88 |
num_rows: 16407
|
89 |
})
|
90 |
})
|
91 |
+
|
92 |
```
|
93 |
+
|
94 |
|
95 |
### Training Procedure
|
96 |
|
97 |
|
98 |
#### Preprocessing [optional]
|
99 |
|
100 |
+
```
|
101 |
+
|
102 |
+
trainable params: 4718592 || all params: 3613463424 || trainables%: 0.13058363808693696
|
103 |
|
104 |
+
```
|
105 |
|
106 |
#### Training Hyperparameters
|
107 |
|
|
|
109 |
|
110 |
#### Speeds, Sizes, Times [optional]
|
111 |
|
112 |
+
```json
|
113 |
|
114 |
metrics={'train_runtime': 30766.4612, 'train_samples_per_second': 3.2, 'train_steps_per_second': 0.2,
|
115 |
'total_flos': 1.1252790565109983e+18, 'train_loss': 1.0597990553941183,", true)}}
|
116 |
+
|
117 |
```
|
118 |
|
119 |
## Environmental Impact
|