Downloads · 30 days
24
10% of all-time downloads
llama31-8bn_SFT
NamrataThakur/llama31-8bn_SFT
llama31-8bn_SFT is a question answering model from NamrataThakur. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: NamrataThakur - License: apache-2.0 - Finetuned from model : unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
All-time downloads
230
Public
Parameters
8B
32.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Mar 9, 2026
- Updated
- Mar 13, 2026
- SHA
- 8bd99cdb
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Uploaded finetuned model
- Developed by: NamrataThakur
- License: apache-2.0
- Finetuned from model : unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
| Base Model | Fine-Tuning | Train Dataset | Validation Loss | Evaluation Dataset | Mean Answer Relevancy Score | Mean Answer Correctness Score |
|---|---|---|---|---|---|---|
| Llama3.1-8bn | Supervised Fine-Tuning | GSM8K | 1.12 | SmallThoughts | 0.736 | 0.437 |
- Task
- Question Answering
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en
- Created
- Mar 9, 2026
- Updated
- Mar 13, 2026