worden1/ultra-feedback-paired
Viewer • Updated • 398k • 32 • 1
How to use Loewolf/L-GPT_1.1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Loewolf/L-GPT_1.1") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Loewolf/L-GPT_1.1")
model = AutoModelForCausalLM.from_pretrained("Loewolf/L-GPT_1.1")How to use Loewolf/L-GPT_1.1 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Loewolf/L-GPT_1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Loewolf/L-GPT_1.1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Loewolf/L-GPT_1.1
How to use Loewolf/L-GPT_1.1 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Loewolf/L-GPT_1.1" \
--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": "Loewolf/L-GPT_1.1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "Loewolf/L-GPT_1.1" \
--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": "Loewolf/L-GPT_1.1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Loewolf/L-GPT_1.1 with Docker Model Runner:
docker model run hf.co/Loewolf/L-GPT_1.1
| Aufgaben | L-GPT_1 | L-GPT_1.1 |
|---|---|---|
| Q&A | 7.5% | 44.17% |
L-GPT 1
:
0 Hallo, wie geht es dir?
5 was kannst du?
5 Schreib eine Geschichte.
0 magst du mich?
5 Was bedeutet PC?
30 Was ist google?
punkt zahl:45
L-GPT 1.1
:
100 Hallo, wie geht es dir?
5 was kannst du?
5 Schreib eine Geschichte.
20 magst du mich?
45 Was bedeutet PC?
90 Was ist google?
Punkt Zahl:265