How to use from
SGLangUse 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 "kcoopermiller/llm-jp-1.3b-v1.0-aya" \
--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": "kcoopermiller/llm-jp-1.3b-v1.0-aya",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
llm-jp-1.3b-v1.0-aya
llm-jp's llm-jp-1.3b-v1.0 model fine-tuned on the Japanese examples from Cohere's aya dataset
| Model | llm-jp-eval AVG |
|---|---|
| kcoopermiller/llm-jp-1.3b-v1.0-aya | 0.0698 |
| llm-jp/llm-jp-1.3b-v1.0 | 0.047 |
How to use
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kcoopermiller/llm-jp-1.3b-v1.0-aya")
model = AutoModelForCausalLM.from_pretrained("kcoopermiller/llm-jp-1.3b-v1.0-aya", device_map="auto")
text = "自然言語処理とは何か"
tokenized_input = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt").to(model.device)
with torch.no_grad():
output = model.generate(
tokenized_input,
max_new_tokens=20,
do_sample=True,
top_p=0.90,
temperature=0.7,
)[0]
print(tokenizer.decode(output))
- Downloads last month
- 19
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "kcoopermiller/llm-jp-1.3b-v1.0-aya" \ --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": "kcoopermiller/llm-jp-1.3b-v1.0-aya", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'