Downloads · 30 days
10
11% of all-time downloads
CRD_V7
kinzakhan1/CRD_V7
CRD_V7 is a machine learning model from kinzakhan1. 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 llama3.1.
Fine-tuned Llama 3.1 8B on Clinical Reasoning Dataset using research-optimized hyperparameters based on Med42 clinical LLM study and "LoRA Without Regret" findings.
All-time downloads
88
Public
Parameters
8B
16.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.7 GB · 100%
At a glance
- License
- llama3.1
- Model type
- llama
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 24, 2025
- SHA
- 859b549a
Base models
Model card
From the Hugging Face model README
CRD_V7 - Clinical Reasoning Model (Research-Optimized)
Overview
Fine-tuned Llama 3.1 8B on Clinical Reasoning Dataset using research-optimized hyperparameters based on Med42 clinical LLM study and "LoRA Without Regret" findings.
Dataset
- Source: Clinical Reasoning Data (crd_medprompt_unsloth.json)
- Examples: 10,081
- Format: Structured reasoning with "Key facts → Mechanism → Why-not alternatives → <final>"
- Avg Tokens: ~700 per example
Research-Optimized Configuration
| Parameter | Value | Research Basis |
|---|---|---|
| Learning Rate | 0.0001 | Med42: 1e-4 optimal for clinical |
| LoRA Rank | 64 | Higher rank for complex patterns |
| LoRA Alpha | 128 | 2× rank standard |
| LoRA Dropout | 0.05 | Regularization for structured output |
| Target Modules | All (MLP + Attention) | MLP critical for reasoning |
| Epochs | 3 | Structured formats need more exposure |
| Batch Size | 16 | Research-optimal for LoRA |
| Warmup | 5% | Stability for complex learning |
| RSLoRA | Enabled | Rank-stabilized for r≥64 |
Training Results
- Training Time: 2.66 hours
- Final Loss: 0.5773
Part of Experiment
Testing hypothesis: Clinical reasoning data improves general reasoning capabilities.
- kinzakhan1/CRD_V7 - 100% Clinical (this model)
- kinzakhan1/SRD_V7 - 100% Standard reasoning
- kinzakhan1/MIXED_V7 - 50/50 mix
- Type
- llama
- License
- llama3.1
- Created
- Dec 23, 2025
- Updated
- Dec 24, 2025