Downloads · 30 days
0
Student-Focus-mistral-7b-instruct-v0.3
arafatanam/Student-Focus-mistral-7b-instruct-v0.3
Student-Focus-mistral-7b-instruct-v0.3 is a machine learning model from arafatanam. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a fine-tuned version of unsloth/mistral-7b-instruct-v0.3-bnb-4bit, designed for mental health counseling. It enhances response quality in mental health discussions, providing empathetic and well-structured rep…
Access
Public
Updated Apr 3, 2025
Repo size
168 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors168 MB · 97%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025
- SHA
- 84327ef1
Base models
Model card
From the Hugging Face model README
Mistral-7B-Instruct Fine-Tuned for Mental Health Counseling
Model Overview
This is a fine-tuned version of unsloth/mistral-7b-instruct-v0.3-bnb-4bit, designed for mental health counseling. It enhances response quality in mental health discussions, providing empathetic and well-structured replies.
Dataset
- Amod/mental_health_counseling_conversations (cleaned version:
arafatanam/Mental-Health-Counseling) - 2752 rows - chillies/student-mental-health-counseling-vn (translated version:
arafatanam/Student-Mental-Health-Counseling-10K) - 7500 rows - Total dataset size: 10,252 rows
Training Details
- Hardware: Kaggle Notebooks (GPU T4 x2)
- Fine-tuning framework:
UnslothwithLoRA - Training settings:
max_seq_length = 512batch_size = 8gradient_accumulation_steps = 4num_train_epochs = 2learning_rate = 5e-5optimizer = adamw_8bitlr_scheduler = cosine
Training Results
- Final training loss:
1.0042 - Total steps:
640 - Trainable parameters:
0.60%of the model` - Validation loss:
0.978 - Evaluation metric (perplexity):
2.85
Usage
This model is best suited for:
- Mental health chatbots
- Virtual therapy applications
- Mental health support and response generation
- License
- apache-2.0
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025