Instructions to use LumiOpen/Poro-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LumiOpen/Poro-34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LumiOpen/Poro-34B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LumiOpen/Poro-34B") model = AutoModelForCausalLM.from_pretrained("LumiOpen/Poro-34B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LumiOpen/Poro-34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LumiOpen/Poro-34B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LumiOpen/Poro-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LumiOpen/Poro-34B
- SGLang
How to use LumiOpen/Poro-34B 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 "LumiOpen/Poro-34B" \ --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": "LumiOpen/Poro-34B", "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 "LumiOpen/Poro-34B" \ --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": "LumiOpen/Poro-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LumiOpen/Poro-34B with Docker Model Runner:
docker model run hf.co/LumiOpen/Poro-34B
Add Finnish and English language metadata tags
#3
by fergusq - opened
README.md
CHANGED
|
@@ -5,6 +5,9 @@ datasets:
|
|
| 5 |
- bigcode/starcoderdata
|
| 6 |
- mc4
|
| 7 |
- allenai/dolma
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
<div align="center">
|
| 10 |
<img src="./poro-logo.png" width="200px">
|
|
@@ -121,4 +124,4 @@ Poro is an advanced language model, primarily optimized for English, Finnish and
|
|
| 121 |
|
| 122 |
## License
|
| 123 |
|
| 124 |
-
Poro is released under the Apache 2.0 license.
|
|
|
|
| 5 |
- bigcode/starcoderdata
|
| 6 |
- mc4
|
| 7 |
- allenai/dolma
|
| 8 |
+
language:
|
| 9 |
+
- fi
|
| 10 |
+
- en
|
| 11 |
---
|
| 12 |
<div align="center">
|
| 13 |
<img src="./poro-logo.png" width="200px">
|
|
|
|
| 124 |
|
| 125 |
## License
|
| 126 |
|
| 127 |
+
Poro is released under the Apache 2.0 license.
|