Downloads · 30 days
14
2% of all-time downloads
phillama-3.8b-v1
raincandy-u/phillama-3.8b-v1
phillama-3.8b-v1 is a text generation model from raincandy-u. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
All-time downloads
612
Public
Parameters
3.8B
7.6 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors7.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Apr 28, 2024
- Updated
- Apr 28, 2024
- SHA
- 67ebe44f
Try a prompt
Model card
From the Hugging Face model README
phillama-3.8b-v1
Phillama is a model based on Phi-3-mini and trained on Llama-generated datasets to make it more "llama-like".
Also, this model is converted into Llama format, so it will work with any Llama-2/3 workflow.
Dataset
| Source | Task | Number of examples（k） |
|---|---|---|
| lmsys-1m | Chat | 50 |
| dolphin-coder | Code | 10 |
| slimorca | Reasoning | 10 |
System prompt
You are a humanoid AI assistant. You think step by step and give detailed long response.
Prompt template
<|system|>
You are a humanoid AI assistant. You think step by step and give detailed long response.<|end|>
<|user|>
Why people like llama?<|end|>
<|assistant|>
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- mit
- Created
- Apr 28, 2024
- Updated
- Apr 28, 2024