Instructions to use zstanjj/SlimPLM-Query-Rewriting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zstanjj/SlimPLM-Query-Rewriting with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zstanjj/SlimPLM-Query-Rewriting")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zstanjj/SlimPLM-Query-Rewriting")
model = AutoModelForCausalLM.from_pretrained("zstanjj/SlimPLM-Query-Rewriting")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zstanjj/SlimPLM-Query-Rewriting with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zstanjj/SlimPLM-Query-Rewriting"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zstanjj/SlimPLM-Query-Rewriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zstanjj/SlimPLM-Query-Rewriting

SGLang

How to use zstanjj/SlimPLM-Query-Rewriting 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 "zstanjj/SlimPLM-Query-Rewriting" \
    --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": "zstanjj/SlimPLM-Query-Rewriting",
		"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 "zstanjj/SlimPLM-Query-Rewriting" \
        --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": "zstanjj/SlimPLM-Query-Rewriting",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zstanjj/SlimPLM-Query-Rewriting with Docker Model Runner:
```
docker model run hf.co/zstanjj/SlimPLM-Query-Rewriting
```

zstanjj commited on Nov 29, 2024

Commit

cea2117

verified ·

1 Parent(s): b10750c

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -37,6 +37,12 @@ heuristic_answer = "The voice of Darth Vader in Star Wars is provided by British
 prompt = (f"<s>[INST] <<SYS>>\nYou are a helpful assistant. Your task is to parse user input into"
           f" structured formats according to the coarse answer. Current datatime is 2023-12-20 9:47:28"
           f" <</SYS>>\n Course answer: (({heuristic_answer}))\nQuestion: (({question})) [/INST]")
 params_query_rewrite = {"repetition_penalty": 1.05, "temperature": 0.01, "top_k": 1, "top_p": 0.85,
                         "max_new_tokens": 512, "do_sample": False, "seed": 2023}

 prompt = (f"<s>[INST] <<SYS>>\nYou are a helpful assistant. Your task is to parse user input into"
           f" structured formats according to the coarse answer. Current datatime is 2023-12-20 9:47:28"
           f" <</SYS>>\n Course answer: (({heuristic_answer}))\nQuestion: (({question})) [/INST]")
+# alternatively you can input question only
+# prompt = (f"<s>[INST] <<SYS>>\nYou are a helpful assistant. Your task is to parse user input into"
+#           f" structured formats. Current datatime is 2023-12-20 9:47:28"
+#           f" <</SYS>>\n{question} [/INST]")
 params_query_rewrite = {"repetition_penalty": 1.05, "temperature": 0.01, "top_k": 1, "top_p": 0.85,
                         "max_new_tokens": 512, "do_sample": False, "seed": 2023}