Downloads · 30 days
14
12% of all-time downloads
MIXED_V7
kinzakhan1/MIXED_V7
MIXED_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.
- Source: mixedcrdcot10kunsloth.jsonl - Examples: 10,000 - Format: messages[] chat format (mixture of structured clinical + general reasoning)
All-time downloads
116
Public
Parameters
8B
16.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- License
- llama3.1
- Model type
- llama
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 24, 2025
- SHA
- 5e19d6dc
Base models
Model card
From the Hugging Face model README
MIXED_V7 - Mixed (CRD+SRD) Model (V7)
Dataset
- Source: mixed_crd_cot_10k_unsloth.jsonl
- Examples: 10,000
- Format: messages[] chat format (mixture of structured clinical + general reasoning)
Training Configuration
| Parameter | Value |
|---|---|
| Learning Rate | 0.00012 |
| LoRA Rank | 48 |
| LoRA Alpha | 96 |
| LoRA Dropout | 0.025 |
| Target Modules | All (MLP + Attention) |
| Epochs | 3 |
| Batch Size (effective) | 16 |
| Warmup | 4% |
| RSLoRA | Enabled |
Training Results
- Training Time: 2.57 hours
- Final Loss: 0.7364
- Type
- llama
- License
- llama3.1
- Created
- Dec 23, 2025
- Updated
- Dec 24, 2025