totally-not-an-llm/EverythingLM-data-V3
Viewer • Updated • 1.07k • 37 • 32
How to use TinyPixel/stablelm-ft2 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="TinyPixel/stablelm-ft2", trust_remote_code=True) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("TinyPixel/stablelm-ft2", trust_remote_code=True, dtype="auto")How to use TinyPixel/stablelm-ft2 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TinyPixel/stablelm-ft2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "TinyPixel/stablelm-ft2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/TinyPixel/stablelm-ft2
How to use TinyPixel/stablelm-ft2 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "TinyPixel/stablelm-ft2" \
--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": "TinyPixel/stablelm-ft2",
"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 "TinyPixel/stablelm-ft2" \
--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": "TinyPixel/stablelm-ft2",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use TinyPixel/stablelm-ft2 with Docker Model Runner:
docker model run hf.co/TinyPixel/stablelm-ft2
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("TinyPixel/stablelm-ft2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TinyPixel/stablelm-ft2", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
text = '''### System:
You are a helpful AI assistant.
### User:
Why is sky blue?
### Assistant:
'''
device = "cuda:0"
inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs,
max_new_tokens=512,
do_sample=True,
top_p=0.95,
temperature=0.7,
top_k=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=False))