Downloads · 30 days
20
14% of all-time downloads
gparag_tinyllama-1.1b-finetuned-gguf
gparag/gparag_tinyllama-1.1b-finetuned-gguf
gparag_tinyllama-1.1b-finetuned-gguf is a text generation model from gparag. Use it when you need the model to write or continue text. It is set up for llama-cpp. The card lists the license as apache-2.0.
Custom 1.1B model fine-tuned for concise chat!
All-time downloads
138
Public
Repo size
668 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf668 MB · 100%
At a glance
- Task
- Text Generation
- Library
- llama-cpp
- License
- apache-2.0
- Access
- Public
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026
- SHA
- a4fc3980
Try a prompt
Base models
Model card
From the Hugging Face model README
TinyLlama (Fine-Tuned)
Custom 1.1B model fine-tuned for concise chat!
🎯 Optimized For
- Mobile devices (Android/iOS)
- Real-time chat (llama.cpp)
- Concise responses (1-3 sentences)
📊 Model Details
| Parameter | Value |
|---|---|
| Base Model | TinyLlama-1.1B-Chat-v1.0 |
| Fine-tuned | Unsloth + LoRA (r=16) |
| Dataset | Guanaco/ShareGPT (5K chat pairs) |
| Quantization | Q4_K_M (637MB) |
| Context | 2048 tokens |
| Vocab | 32,000 |
Training Details
- Epochs: 3
- LoRA Rank: 16
- Learning Rate: 2e-4
- Batch Size: 2 (gradient accumulation: 4)
- Framework: Unsloth + TRL
- Task
- Text Generation
- Library
- llama-cpp
- License
- apache-2.0
- Languages
- en
- Created
- Jan 30, 2026
- Updated
- Jan 30, 2026