Text Generation
Transformers
PyTorch
Safetensors
English
Korean
llama
Yi-Ko
01-ai
Yi
Eval Results (legacy)
text-generation-inference
Instructions to use beomi/Yi-Ko-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beomi/Yi-Ko-6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beomi/Yi-Ko-6B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("beomi/Yi-Ko-6B") model = AutoModelForCausalLM.from_pretrained("beomi/Yi-Ko-6B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use beomi/Yi-Ko-6B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beomi/Yi-Ko-6B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "beomi/Yi-Ko-6B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/beomi/Yi-Ko-6B
- SGLang
How to use beomi/Yi-Ko-6B 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 "beomi/Yi-Ko-6B" \ --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": "beomi/Yi-Ko-6B", "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 "beomi/Yi-Ko-6B" \ --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": "beomi/Yi-Ko-6B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use beomi/Yi-Ko-6B with Docker Model Runner:
docker model run hf.co/beomi/Yi-Ko-6B
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ tags:
|
|
| 20 |
library_name: transformers
|
| 21 |
---
|
| 22 |
|
|
|
|
|
|
|
| 23 |
> Update @ 2023.12.03 Yi-Ko(KoEN)-6B Achieved #1π₯ Pretrained Models at [Open Korean LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)! π
|
| 24 |
|
| 25 |
> Update @ 2023.12.01 Alpha Release of Yi-Ko(KoEN)-6B model π
|
|
|
|
| 20 |
library_name: transformers
|
| 21 |
---
|
| 22 |
|
| 23 |
+
> Update @ 2024.01.29 New Model [beomi/Yi-Ko-DUS-9B](https://huggingface.co/beomi/Yi-Ko-DUS-9B) Released! π
|
| 24 |
+
|
| 25 |
> Update @ 2023.12.03 Yi-Ko(KoEN)-6B Achieved #1π₯ Pretrained Models at [Open Korean LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)! π
|
| 26 |
|
| 27 |
> Update @ 2023.12.01 Alpha Release of Yi-Ko(KoEN)-6B model π
|