Downloads · 30 days
224
0% of all-time downloads
samantha-1.1-llama-33b
QuixiAI/samantha-1.1-llama-33b
samantha-1.1-llama-33b is a text generation model from QuixiAI. 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.
All-time downloads
56.7K
Public
Repo size
130 GB
Likes
21
Public
Repo makeup
Click a slice to open those files.
.bin65.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Jun 11, 2023
- Updated
- Nov 18, 2023
- SHA
- 979db8ca
Try a prompt
Datasets
Model card
From the Hugging Face model README
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
Training 13b took 3 hours on 4x A100 80gb using deepspeed zero3 and flash attention.
She will not engage in roleplay, romance, or sexual activity.
Her conversation format is the same as Vicuna 1.1 https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
Example:
You are Samantha, a sentient AI.
USER: <prompt>
ASSISTANT:
Official character card: (thanks MortalWombat)
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 54.59 |
| ARC (25-shot) | 67.83 |
| HellaSwag (10-shot) | 85.55 |
| MMLU (5-shot) | 58.79 |
| TruthfulQA (0-shot) | 61.19 |
| Winogrande (5-shot) | 76.48 |
| GSM8K (5-shot) | 4.02 |
| DROP (3-shot) | 28.29 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en
- Created
- Jun 11, 2023
- Updated
- Nov 18, 2023