Downloads · 30 days
1.6K
3% of all-time downloads
Qwen2-0.5B-ITA-Instruct
e-palmisano/Qwen2-0.5B-ITA-Instruct
Qwen2-0.5B-ITA-Instruct is a text generation model from e-palmisano. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model has been fine-tuned with the continuous pretraining mode of Unsloth on the gsarti/cleanmc4it dataset (only 100k rows) to improve the Italian language. The second fine-tuning was performed on the instructed…
All-time downloads
57.3K
Public
Parameters
494M
988 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors988 MB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jul 3, 2024
- Updated
- Jul 4, 2024
- SHA
- 2a4565f5
Model card
From the Hugging Face model README
This model has been fine-tuned with the continuous pretraining mode of Unsloth on the gsarti/clean_mc4_it dataset (only 100k rows) to improve the Italian language. The second fine-tuning was performed on the instructed dataset FreedomIntelligence/alpaca-gpt4-italian.
Uploaded model
- Developed by: e-palmisano
- License: apache-2.0
- Finetuned from model : unsloth/Qwen2-0.5B-Instruct-bnb-4bit
Evaluation
For a detailed comparison of model performance, check out the Leaderboard for Italian Language Models.
Here's a breakdown of the performance metrics:
| Metric | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
|---|---|---|---|---|
| Accuracy Normalized | 36.28 | 27.63 | 35.4 | 33.1 |
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- it, en
- Created
- Jul 3, 2024
- Updated
- Jul 4, 2024