Update README.md
Browse files
README.md
CHANGED
|
@@ -12,12 +12,12 @@ datasets:
|
|
| 12 |
- OEvortex/EmotionalIntelligence-10K
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# HelpingAI-9B: Emotionally Intelligent Conversational AI
|
| 16 |
|
| 17 |

|
| 18 |
|
| 19 |
## Overview
|
| 20 |
-
HelpingAI-9B 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.
|
| 21 |
|
| 22 |
## Objectives
|
| 23 |
- Engage in open-ended dialogue while displaying emotional intelligence
|
|
@@ -25,16 +25,17 @@ HelpingAI-9B is a large language model designed for emotionally intelligent conv
|
|
| 25 |
- Provide supportive, empathetic, and psychologically-grounded responses
|
| 26 |
- Avoid insensitive, harmful, or unethical speech
|
| 27 |
- Continuously improve emotional awareness and dialogue skills
|
|
|
|
| 28 |
|
| 29 |
## Methodology
|
| 30 |
-
HelpingAI-9B is based on the HelpingAI series and further trained using:
|
| 31 |
- Supervised learning on large dialogue datasets with emotional labeling
|
| 32 |
- Reinforcement learning with a reward model favoring emotionally supportive responses
|
| 33 |
- Constitution training to instill stable and beneficial objectives
|
| 34 |
- Knowledge augmentation from psychological resources on emotional intelligence
|
| 35 |
|
| 36 |
## Emotional Quotient (EQ)
|
| 37 |
-
HelpingAI-9B has achieved an impressive Emotional Quotient (EQ) of 89.23, surpassing almost all AI models in emotional intelligence. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.
|
| 38 |
|
| 39 |

|
| 40 |
|
|
@@ -43,11 +44,11 @@ HelpingAI-9B has achieved an impressive Emotional Quotient (EQ) of 89.23, surpas
|
|
| 43 |
import torch
|
| 44 |
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
| 45 |
|
| 46 |
-
# Let's bring in the big guns! Our super cool HelpingAI-9B model
|
| 47 |
-
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B").to("cuda")
|
| 48 |
|
| 49 |
# We also need the special HelpingAI translator to understand our chats
|
| 50 |
-
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B")
|
| 51 |
|
| 52 |
# This TextStreamer thingy is our secret weapon for super smooth conversation flow
|
| 53 |
streamer = TextStreamer(tokenizer)
|
|
@@ -95,8 +96,8 @@ import os
|
|
| 95 |
|
| 96 |
|
| 97 |
# 1. Download the model
|
| 98 |
-
repo_id = "OEvortex/HelpingAI-9B"
|
| 99 |
-
filename = "
|
| 100 |
model_path = download_model(repo_id, filename, os.environ.get("hf_token"))
|
| 101 |
|
| 102 |
# 2. Load the model
|
|
@@ -116,7 +117,7 @@ sampler = SamplerSettings(temp=0.7, top_p=0.9)ย # Adjust these values as needed
|
|
| 116 |
thread = Thread(model, custom_chatml, sampler=sampler)
|
| 117 |
|
| 118 |
# 7. Start interacting with the model
|
| 119 |
-
thread.interact(header="๐ HelpingAI-9B: Emotionally Intelligent Conversational AI ๐", color=True)
|
| 120 |
```
|
| 121 |
## Example Dialogue
|
| 122 |
> Express joy and excitement about visiting a new place.
|
|
|
|
| 12 |
- OEvortex/EmotionalIntelligence-10K
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# HelpingAI-9B-200k: Emotionally Intelligent Conversational AI with 200k context window
|
| 16 |
|
| 17 |

|
| 18 |
|
| 19 |
## Overview
|
| 20 |
+
HelpingAI-9B-200k 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.
|
| 21 |
|
| 22 |
## Objectives
|
| 23 |
- Engage in open-ended dialogue while displaying emotional intelligence
|
|
|
|
| 25 |
- Provide supportive, empathetic, and psychologically-grounded responses
|
| 26 |
- Avoid insensitive, harmful, or unethical speech
|
| 27 |
- Continuously improve emotional awareness and dialogue skills
|
| 28 |
+
- High Context length
|
| 29 |
|
| 30 |
## Methodology
|
| 31 |
+
HelpingAI-9B-200k is based on the HelpingAI series and further trained using:
|
| 32 |
- Supervised learning on large dialogue datasets with emotional labeling
|
| 33 |
- Reinforcement learning with a reward model favoring emotionally supportive responses
|
| 34 |
- Constitution training to instill stable and beneficial objectives
|
| 35 |
- Knowledge augmentation from psychological resources on emotional intelligence
|
| 36 |
|
| 37 |
## Emotional Quotient (EQ)
|
| 38 |
+
HelpingAI-9B-200k has achieved an impressive Emotional Quotient (EQ) of 89.23, surpassing almost all AI models in emotional intelligence. This EQ score reflects its advanced ability to understand and respond to human emotions in a supportive and empathetic manner.
|
| 39 |
|
| 40 |

|
| 41 |
|
|
|
|
| 44 |
import torch
|
| 45 |
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
| 46 |
|
| 47 |
+
# Let's bring in the big guns! Our super cool HelpingAI-9B-200k model
|
| 48 |
+
model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-9B-200k-200k").to("cuda")
|
| 49 |
|
| 50 |
# We also need the special HelpingAI translator to understand our chats
|
| 51 |
+
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-9B-200k-200k")
|
| 52 |
|
| 53 |
# This TextStreamer thingy is our secret weapon for super smooth conversation flow
|
| 54 |
streamer = TextStreamer(tokenizer)
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
# 1. Download the model
|
| 99 |
+
repo_id = "OEvortex/HelpingAI-9B-200k-200k"
|
| 100 |
+
filename = "HelpingAI-9B-200k.Q4_0.gguf"
|
| 101 |
model_path = download_model(repo_id, filename, os.environ.get("hf_token"))
|
| 102 |
|
| 103 |
# 2. Load the model
|
|
|
|
| 117 |
thread = Thread(model, custom_chatml, sampler=sampler)
|
| 118 |
|
| 119 |
# 7. Start interacting with the model
|
| 120 |
+
thread.interact(header="๐ HelpingAI-9B-200k: Emotionally Intelligent Conversational AI ๐", color=True)
|
| 121 |
```
|
| 122 |
## Example Dialogue
|
| 123 |
> Express joy and excitement about visiting a new place.
|