Abhaykoul commited on
Commit
405eb11
β€’
1 Parent(s): e331317

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -170
README.md CHANGED
@@ -1,199 +1,94 @@
1
  ---
2
- library_name: transformers
3
- tags: []
4
- ---
5
-
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
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 πŸ€— transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
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
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
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
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
 
78
- ### Training Data
79
-
80
- <!-- 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. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
 
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
 
145
- 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).
146
 
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
 
153
- ## Technical Specifications [optional]
 
 
 
 
 
154
 
155
- ### Model Architecture and Objective
 
 
 
 
 
156
 
157
- [More Information Needed]
 
158
 
159
- ### Compute Infrastructure
 
 
 
160
 
161
- [More Information Needed]
 
162
 
163
- #### Hardware
 
164
 
165
- [More Information Needed]
 
166
 
167
- #### Software
 
 
 
 
 
 
 
168
 
169
- [More Information Needed]
 
170
 
171
- ## Citation [optional]
172
 
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
174
 
175
- **BibTeX:**
 
176
 
177
- [More Information Needed]
 
178
 
179
- **APA:**
 
180
 
181
- [More Information Needed]
182
 
183
- ## Glossary [optional]
 
184
 
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
 
187
- [More Information Needed]
188
 
189
- ## More Information [optional]
190
 
191
- [More Information Needed]
192
 
193
- ## Model Card Authors [optional]
194
 
195
- [More Information Needed]
196
 
197
- ## Model Card Contact
198
 
199
- [More Information Needed]
 
1
  ---
2
+ license: other
3
+ license_name: helpingai
4
+ license_link: LICENSE.md
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - HelpingAI
8
+ - Emotionally Intelligent
9
+ - EQ
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
 
11
+ ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
 
13
+ # HelpingAI-3B: Emotionally Intelligent Conversational AI
14
 
15
+ ![logo](https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png)
16
 
17
+ ## Overview
18
+ HelpingAI-3B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
 
 
 
19
 
20
+ ## Objectives
21
+ - Engage in open-ended dialogue while displaying emotional intelligence
22
+ - Recognize and validate user emotions and emotional contexts
23
+ - Provide supportive, empathetic, and psychologically-grounded responses
24
+ - Avoid insensitive, harmful, or unethical speech
25
+ - Continuously improve emotional awareness and dialogue skills
26
 
27
+ ## Methodology
28
+ HelpingAI-3B is based on the HelpingAI series and further trained using:
29
+ - Supervised learning on large dialogue datasets with emotional labeling
30
+ - Reinforcement learning with a reward model favoring emotionally supportive responses
31
+ - Constitution training to instill stable and beneficial objectives
32
+ - Knowledge augmentation from psychological resources on emotional intelligence
33
 
34
+ ## Emotional Quotient (EQ)
35
+ NOT tested yet
36
 
37
+ ## Usage code
38
+ ```python
39
+ import torch
40
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
41
 
42
+ # Let's bring in the big guns! Our super cool HelpingAI-3B model
43
+ model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-3B-v3", trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
44
 
45
+ # We also need the special HelpingAI translator to understand our chats
46
+ tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-3B-v3", trust_remote_code=True, torch_dtype=torch.float16)
47
 
48
+ # This TextStreamer thingy is our secret weapon for super smooth conversation flow
49
+ streamer = TextStreamer(tokenizer)
50
 
51
+ # Now, here comes the magic! ✨ This is the basic template for our chat
52
+ prompt = """
53
+ <|im_start|>system: {system}
54
+ <|im_end|>
55
+ <|im_start|>user: {insaan}
56
+ <|im_end|>
57
+ <|im_start|>assistant:
58
+ """
59
 
60
+ # Okay, enough chit-chat, let's get down to business! Here's what will be our system prompt
61
+ system = "You are HelpingAI a emotional AI always answer my question in HelpingAI-style"
62
 
 
63
 
64
+ # And the insaan is curious (like you!) insaan means human in hindi
65
+ insaan = "I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone."
66
 
67
+ # Now we combine system and user messages into the template, like adding sprinkles to our conversation cupcake
68
+ prompt = prompt.format(system=system, insaan=insaan)
69
 
70
+ # Time to chat! We'll use the tokenizer to translate our text into a language the model understands
71
+ inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False).to("cuda")
72
 
73
+ # Here comes the fun part! Let's unleash the power of HelpingAI-3B to generate some awesome text
74
+ generated_text = model.generate(**inputs, max_length=3084, top_p=0.95, do_sample=True, temperature=0.6, use_cache=True, streamer=streamer)
75
 
76
+ ```
77
 
78
+ ## Example Dialogue
79
+ > Express joy and excitement about visiting a new place.
80
 
81
+ Yay! πŸŽ‰ Excitement is the best thing we can experience! 🌟 Get ready to explore new places, learn something new, and meet amazing people! 🌈 Let's go on an adventure together! 🌟
82
 
83
+ > I'm excited because I just got accepted into my dream school! I wanted to share the good news with someone.
84
 
85
+ That's awesome! 🌟 I'd love to hear more about it! Sharing good news is always a pleasure. Which school is it and how did you feel when you got accepted? Remember, I'm here to support you and celebrate your achievements! πŸŽ‰πŸŒˆπŸŒŸ
86
 
87
+ > My best friend just got into an argument with me and I don't know what to do. How can I fix this situation?
88
 
89
+ It is always tough when friends have misunderstandings, but it's important to communicate and work through the problem together. You can start by talking to your friend and trying to understand their perspective. It's also helpful to be empathetic and supportive, and to listen to their point of view. Remember, conflicts are a part of any relationship, and it's how you handle them that matters. Good luck! 🌟
90
 
91
+ > How can you identify the emotions of others based on their body language and facial expressions?
92
 
93
+ πŸ€” Understanding body language and facial expressions can be a complex task, but I can definitely help you with that! 😊 When someone is feeling happy, their face might smile, their eyes might light up, and they might have an open and relaxed posture. Worrying or sadness might be shown through furrowed brows, a tense posture, and a downturned mouth. Anger might be shown through clenched teeth, a furrowed brow, and a tense body language. Love and affection might be shown through a heart-shaped face, a smile, and open arms. These are just generalizations, and there can be a wide range of emotions people express, but it's a good starting point for understanding body language and facial expressions. If you want to learn more, I'm here to help! 😊
94