Downloads · 30 days
47
0% of all-time downloads
Orca-2-13b-SFT-v6
Locutusque/Orca-2-13b-SFT-v6
Orca-2-13b-SFT-v6 is a text generation model from Locutusque. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/norobots, totally-not-an-llm/EverythingLM-data-V3, LDJnr/Capybara, LDJnr/Pure-Dove, LDJnr/LessWrong-Amplify-Instruct, LDJnr/Verified-Camel, mlabonne/g…
All-time downloads
188K
Public
Parameters
13B
64 GB on disk
Likes
10
Public
Repo makeup
Click a slice to open those files.
.safetensors26 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Dec 22, 2023
- Updated
- Mar 4, 2024
- SHA
- a275f3e7
Try a prompt
Base models
Model card
From the Hugging Face model README
The "microsoft/Orca-2-13b" model fully fine-tuned on HuggingFaceH4/no_robots, totally-not-an-llm/EverythingLM-data-V3, LDJnr/Capybara, LDJnr/Pure-Dove, LDJnr/LessWrong-Amplify-Instruct, LDJnr/Verified-Camel, mlabonne/guanaco-llama2-1k, and OpenAssistant/oasst_top1_2023-08-25. This model achieved a test loss of 0.39 on LDJnr/Verified-Camel.
Make sure to comply with the microsoft research license. Please read it before using this model.
This model was trained on the ChatML prompt template.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 56.15 |
| AI2 Reasoning Challenge (25-Shot) | 60.41 |
| HellaSwag (10-Shot) | 80.46 |
| MMLU (5-Shot) | 59.51 |
| TruthfulQA (0-shot) | 54.01 |
| Winogrande (5-shot) | 77.43 |
| GSM8k (5-shot) | 5.08 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en, fr, es, hi, zh, code
- Created
- Dec 22, 2023
- Updated
- Mar 4, 2024