Downloads · 30 days
67
0% of all-time downloads
Orca-2-13b-SFT-v4
Locutusque/Orca-2-13b-SFT-v4
Orca-2-13b-SFT-v4 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, mlabonne/guanaco-llama2-1k, and OpenAssistant/oassttop12023-08-25. This model achieved a test loss…
All-time downloads
213K
Public
Parameters
13B
144 GB on disk
Likes
5
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
- Nov 25, 2023
- Updated
- Dec 19, 2023
- SHA
- f3491a4c
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, mlabonne/guanaco-llama2-1k, and OpenAssistant/oasst_top1_2023-08-25. This model achieved a test loss of 0.18.
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.
The responses seen in the inference API were generated using the following sampling parameters:
temperature = 0.1
top_p = 0.14
top_k = 41
repetition_penalty = 1.176
Updates:
12/18/23 - 🔥 This model holds the #5 position on the Open LLM Leaderboard among llama2-13b models. 🔥
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en, fr, es, hi, zh, code
- Created
- Nov 25, 2023
- Updated
- Dec 19, 2023