Update README.md
Browse files
README.md
CHANGED
@@ -20,6 +20,106 @@ library_name: transformers
|
|
20 |
- **License:** apache-2.0
|
21 |
- **Finetuned from model :** unsloth/tinyllama
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
24 |
|
25 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
20 |
- **License:** apache-2.0
|
21 |
- **Finetuned from model :** unsloth/tinyllama
|
22 |
|
23 |
+
<style>
|
24 |
+
img{
|
25 |
+
width: 45vw;
|
26 |
+
height: 45vh;
|
27 |
+
margin: 0 auto;
|
28 |
+
display: flex;
|
29 |
+
align-items: center;
|
30 |
+
justify-content: center;
|
31 |
+
}
|
32 |
+
</style>
|
33 |
+
|
34 |
+
# ShieldX/manovyadh-1.1B-v1
|
35 |
+
|
36 |
+
Introducing ManoVyadh by LumaticAI. A finetuned version of TinyLlama 1.1B Chat on Mental Health Counselling Dataset.
|
37 |
+
|
38 |
+
|
39 |
+
<img class="custom-image" src="manovyadh.png" alt="BongLlama">
|
40 |
+
|
41 |
+
|
42 |
+
# Model Details
|
43 |
+
|
44 |
+
## Model Description
|
45 |
+
|
46 |
+
ManoVyadh is a LLM for mental health counselling.
|
47 |
+
|
48 |
+
# Uses
|
49 |
+
|
50 |
+
## Direct Use
|
51 |
+
|
52 |
+
- base model for further finetuning
|
53 |
+
- for fun
|
54 |
+
|
55 |
+
|
56 |
+
## Downstream Use
|
57 |
+
|
58 |
+
- can be deployed with api
|
59 |
+
- used to create webapp or app to show demo
|
60 |
+
|
61 |
+
|
62 |
+
## Out-of-Scope Use
|
63 |
+
|
64 |
+
- cannot be used for production purpose
|
65 |
+
- not to be applied in real life health purpose
|
66 |
+
- cannot be used to generate text for research or academic purposes
|
67 |
+
|
68 |
+
|
69 |
+
# Bias, Risks, and Limitations
|
70 |
+
|
71 |
+
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
|
72 |
+
|
73 |
+
# Training Details
|
74 |
+
|
75 |
+
# Model Examination
|
76 |
+
|
77 |
+
We will be further finetuning this model on large dataset to see how it performs
|
78 |
+
|
79 |
+
# Environmental Impact
|
80 |
+
|
81 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
82 |
+
|
83 |
+
- **Hardware Type:** 1 X Tesla T4
|
84 |
+
- **Hours used:** 0.30
|
85 |
+
- **Cloud Provider:** Google Colab
|
86 |
+
- **Compute Region:** India
|
87 |
+
|
88 |
+
# Technical Specifications
|
89 |
+
|
90 |
+
## Model Architecture and Objective
|
91 |
+
|
92 |
+
Finetuned on Tiny-Llama 1.1B Chat model
|
93 |
+
|
94 |
+
|
95 |
+
### Hardware
|
96 |
+
|
97 |
+
1 X Tesla T4
|
98 |
+
|
99 |
+
|
100 |
+
# Citation
|
101 |
+
|
102 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
103 |
+
|
104 |
+
**BibTeX:**
|
105 |
+
|
106 |
+
```
|
107 |
+
@misc{ShieldX/manovyadh-1.1B-v1,
|
108 |
+
url={[https://huggingface.co/ShieldX/manovyadh-1.1B-v1](https://huggingface.co/ShieldX/manovyadh-1.1B-v1)},
|
109 |
+
title={ManoVyadh},
|
110 |
+
author={Rohan Shaw},
|
111 |
+
year={2024}, month={Jan}
|
112 |
+
}
|
113 |
+
```
|
114 |
+
|
115 |
+
# Model Card Authors
|
116 |
+
|
117 |
+
ShieldX a.k.a Rohan Shaw
|
118 |
+
|
119 |
+
# Model Card Contact
|
120 |
+
|
121 |
+
email : [email protected]
|
122 |
+
|
123 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
124 |
|
125 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|