Text Generation
Transformers
Safetensors
PyTorch
English
Korean
llama
Yi-Ko
01-ai
Yi
text-generation-inference
Instructions to use beomi/Yi-Ko-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beomi/Yi-Ko-34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beomi/Yi-Ko-34B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("beomi/Yi-Ko-34B") model = AutoModelForCausalLM.from_pretrained("beomi/Yi-Ko-34B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use beomi/Yi-Ko-34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beomi/Yi-Ko-34B" # 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-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/beomi/Yi-Ko-34B
- SGLang
How to use beomi/Yi-Ko-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 "beomi/Yi-Ko-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": "beomi/Yi-Ko-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 "beomi/Yi-Ko-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": "beomi/Yi-Ko-34B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use beomi/Yi-Ko-34B with Docker Model Runner:
docker model run hf.co/beomi/Yi-Ko-34B
Update README.md
Browse files
README.md
CHANGED
|
@@ -103,13 +103,13 @@ Yi-Ko series models are an auto-regressive language model that uses an optimized
|
|
| 103 |
| - haerae_standard_nomenclature| 1|none | 5|acc |0.8301|± |0.0305|
|
| 104 |
| | |none | 5|acc_norm|0.8301|± |0.0305|
|
| 105 |
|
| 106 |
-
## LICENSE
|
| 107 |
-
|
| 108 |
-
Apache 2.0
|
| 109 |
|
| 110 |
-
##
|
| 111 |
|
|
|
|
| 112 |
|
|
|
|
|
|
|
| 113 |
|
| 114 |
## Acknowledgement
|
| 115 |
|
|
|
|
| 103 |
| - haerae_standard_nomenclature| 1|none | 5|acc |0.8301|± |0.0305|
|
| 104 |
| | |none | 5|acc_norm|0.8301|± |0.0305|
|
| 105 |
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
+
## LICENSE
|
| 108 |
|
| 109 |
+
Apache 2.0 (for research)
|
| 110 |
|
| 111 |
+
> For commercial purpose,
|
| 112 |
+
> mailto: jun@beomi.net to acquire Yi-Ko sereis commercial license.
|
| 113 |
|
| 114 |
## Acknowledgement
|
| 115 |
|