Instructions to use rinna/llama-3-youko-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rinna/llama-3-youko-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rinna/llama-3-youko-8b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rinna/llama-3-youko-8b") model = AutoModelForCausalLM.from_pretrained("rinna/llama-3-youko-8b") - Inference
- Local Apps Settings
- vLLM
How to use rinna/llama-3-youko-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rinna/llama-3-youko-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rinna/llama-3-youko-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rinna/llama-3-youko-8b
- SGLang
How to use rinna/llama-3-youko-8b 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 "rinna/llama-3-youko-8b" \ --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": "rinna/llama-3-youko-8b", "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 "rinna/llama-3-youko-8b" \ --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": "rinna/llama-3-youko-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rinna/llama-3-youko-8b with Docker Model Runner:
docker model run hf.co/rinna/llama-3-youko-8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,11 +57,15 @@ The name `youko` comes from the Japanese word [`妖狐/ようこ/Youko`](https:/
|
|
| 57 |
- [Toshiaki Wakatsuki](https://huggingface.co/t-w)
|
| 58 |
- [Kei Sawada](https://huggingface.co/keisawada)
|
| 59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
---
|
| 61 |
|
| 62 |
# Benchmarking
|
| 63 |
|
| 64 |
-
Please refer to [rinna's LM benchmark page](https://rinnakk.github.io/research/benchmarks/lm/index.html).
|
| 65 |
|
| 66 |
---
|
| 67 |
|
|
|
|
| 57 |
- [Toshiaki Wakatsuki](https://huggingface.co/t-w)
|
| 58 |
- [Kei Sawada](https://huggingface.co/keisawada)
|
| 59 |
|
| 60 |
+
* **Release date**
|
| 61 |
+
|
| 62 |
+
May 1, 2024
|
| 63 |
+
|
| 64 |
---
|
| 65 |
|
| 66 |
# Benchmarking
|
| 67 |
|
| 68 |
+
Please refer to [rinna's LM benchmark page (Sheet 20240507)](https://rinnakk.github.io/research/benchmarks/lm/index.html).
|
| 69 |
|
| 70 |
---
|
| 71 |
|