LeoScorpius-GreenNode-Platypus-7B-v1

Model Card for Model ID

This model is a finetuning of other models based on mistralai/Mistral-7B-v0.1.

Model Details

Model Description

The model has been generated from the merging of the models viethq188/LeoScorpius-7B-Chat-DPO and GreenNode/GreenNodeLM-7B-v1olet and a later finetuning with a Platypus dataset garage-bAInd/Open-Platypus.

• Developed by: Ignos
• Model type: Mistral
• License: Apache-2.0

Uses

The model aims to have good overall comparative results on HuggingFace metrics, improving reasoning.

Bias, Risks, and Limitations

The same bias, risks and limitations from base models.

Training Details

Training Data

• garage-bAInd/Open-Platypus

Training Procedure

• Training with QLoRA approach and merging with base model.

Results

• Huggingface evaluation pending

Summary

Technical Specifications

Model Architecture and Objective

• Models based on Mistral Architecture

Compute Infrastructure

• Training on RunPod

Hardware

• 4 x Nvidia RTX 4090
• 64 vCPU 503 GB RAM

Software

• Mergekit (main)
• Axolotl 0.3.0

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: False
• load_in_4bit: True
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: True
• bnb_4bit_compute_dtype: bfloat16

Framework versions

• PEFT 0.6.0