datasets:
- Anthropic/hh-rlhf
- ehartford/dolphin
- conceptofmind/t0_submix_original
- conceptofmind/niv2_submix_original
language:
- en
pipeline_tag: text-generation
Mac Llama 13B
Model Description
`Mac Llama 13B Experimental model is a Llama2 13B model finetuned on an Orca style Dataset
Usage
Mac Llama 13B should be used with this prompt format:
### System:
This is a system prompt, please behave and help the user.
### User:
Your prompt here
### Assistant
The output of Stable Beluga 13B
Model Details
- Model type: Mac Llama 13B is an auto-regressive language model fine-tuned on Llama2 13B.
- Language(s): English
- Library: HuggingFace Transformers
- License: Fine-tuned checkpoints (
Mac Llama 13B) is licensed under the STABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT - Contact: For questions and comments about the model, please email
[email protected]
Training Procedure
Models are learned via supervised fine-tuning on the aforementioned datasets, trained in mixed-precision (BF16), and optimized with AdamW. We outline the following hyperparameters:
| Dataset | Batch Size | Learning Rate | Learning Rate Decay | Warm-up | Weight Decay | Betas |
|---|---|---|---|---|---|---|
| Orca pt1 packed | 256 | 3e-5 | Cosine to 3e-6 | 100 | 1e-6 | (0.9, 0.95) |
Ethical Considerations and Limitations
Beluga is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Beluga's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Beluga, developers should perform safety testing and tuning tailored to their specific applications of the model.