Instructions to use Undi95/ZettaPi-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Undi95/ZettaPi-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Undi95/ZettaPi-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Undi95/ZettaPi-13B") model = AutoModelForCausalLM.from_pretrained("Undi95/ZettaPi-13B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Undi95/ZettaPi-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Undi95/ZettaPi-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Undi95/ZettaPi-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Undi95/ZettaPi-13B
- SGLang
How to use Undi95/ZettaPi-13B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Undi95/ZettaPi-13B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Undi95/ZettaPi-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Undi95/ZettaPi-13B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Undi95/ZettaPi-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Undi95/ZettaPi-13B with Docker Model Runner:
docker model run hf.co/Undi95/ZettaPi-13B
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ Danger Zone (testin').
|
|
| 10 |
<!-- description start -->
|
| 11 |
## Description
|
| 12 |
|
| 13 |
-
This repo contains :
|
| 14 |
<!-- description end -->
|
| 15 |
<!-- description start -->
|
| 16 |
## Models and LoRA used
|
|
@@ -20,7 +20,7 @@ This repo contains : .
|
|
| 20 |
- The-Face-Of-Goonery/Huginn-13b-FP16
|
| 21 |
- CalderaAI/13B-Legerdemain-L2
|
| 22 |
- PygmalionAI/pygmalion-2-13b
|
| 23 |
-
- Undi95/MMSoul-13b-lora
|
| 24 |
<!-- description end -->
|
| 25 |
<!-- prompt-template start -->
|
| 26 |
## Prompt template: Alpaca
|
|
|
|
| 10 |
<!-- description start -->
|
| 11 |
## Description
|
| 12 |
|
| 13 |
+
This repo contains : h̴̙͠i̴̮͝g̷̻̊h̷̞̃ ̶̛̖ḽ̷̋ë̷̥v̶̛̻e̴͕̍ḷ̴̾ ̴̦͝o̶̝̔f̷̣́ ̷̣̔ś̷̪h̵̢͑i̷͕͊t̷̡̉ (just wait testin' phase to end before DL)
|
| 14 |
<!-- description end -->
|
| 15 |
<!-- description start -->
|
| 16 |
## Models and LoRA used
|
|
|
|
| 20 |
- The-Face-Of-Goonery/Huginn-13b-FP16
|
| 21 |
- CalderaAI/13B-Legerdemain-L2
|
| 22 |
- PygmalionAI/pygmalion-2-13b
|
| 23 |
+
- Undi95/MMSoul-13b-lora
|
| 24 |
<!-- description end -->
|
| 25 |
<!-- prompt-template start -->
|
| 26 |
## Prompt template: Alpaca
|