Downloads · 30 days
14
2% of all-time downloads
CodeOptimus-Instruct-Mistral-7B-v0.1.gguf
Jaward/CodeOptimus-Instruct-Mistral-7B-v0.1.gguf
CodeOptimus-Instruct-Mistral-7B-v0.1.gguf is a machine learning model from Jaward. 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 mit.
1. GPU: Requires powerful GPUs - I used 8 Nvidia A100s. 2. Train Time: 1 week. 3. RAG Module: Updates the knowledge base of the model in real-time with adaptive features learned from conversations with the model over…
All-time downloads
837
Public
Repo size
19.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf5.1 GB · 98%
At a glance
- License
- mit
- Access
- Public
- Created
- May 5, 2024
- Updated
- Mar 13, 2025
- SHA
- cdfdd1cf
Model card
From the Hugging Face model README
Finetuned Model For My Thesis: Design And Implementation Of An Adaptive Virtual Intelligent Teaching Assistant Based On Supervised Fine-tuning Of A Pre-trained Large Language Model
Model Name: CodeOptimus - Adaptive Supervised Instruction Fine-tuning Mistral 7B Instruct using qLora.
Prerequisites For Reproduction
- GPU: Requires powerful GPUs - I used 8 Nvidia A100s.
- Train Time: 1 week.
- RAG Module: Updates the knowledge base of the model in real-time with adaptive features learned from conversations with the model over time..
- Python Packages: Install requirements.txt.
- Dataset: Download code_instructions_122k_alpaca_style plus some custom curated dataset
- Mistra-7B-Instruct-v0.1: Download mistralai/Mistral-7B-Instruct-v0.1 pytorch bin weights
- Realistic 3D Intelligent Persona/Avatar (Optional): For this I'm using soulmachine's digital humans.
- License
- mit
- Created
- May 5, 2024
- Updated
- Mar 13, 2025