Instructions to use Wonder-Griffin/XL-Judge-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Wonder-Griffin/XL-Judge-LLM with Transformers:

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

pipe = pipeline("text-generation", model="Wonder-Griffin/XL-Judge-LLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import JudgeXL
model = JudgeXL.from_pretrained("Wonder-Griffin/XL-Judge-LLM", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Wonder-Griffin/XL-Judge-LLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Wonder-Griffin/XL-Judge-LLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Wonder-Griffin/XL-Judge-LLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Wonder-Griffin/XL-Judge-LLM

SGLang

How to use Wonder-Griffin/XL-Judge-LLM 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 "Wonder-Griffin/XL-Judge-LLM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Wonder-Griffin/XL-Judge-LLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Wonder-Griffin/XL-Judge-LLM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Wonder-Griffin/XL-Judge-LLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Wonder-Griffin/XL-Judge-LLM with Docker Model Runner:
```
docker model run hf.co/Wonder-Griffin/XL-Judge-LLM
```

Wonder-Griffin commited on Sep 20, 2024

Commit

9d5fd57

verified ·

1 Parent(s): 29c376d

Update config.json

Browse files

Files changed (1) hide show

config.json +4 -3

config.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-  "_name_or_path": "Wonder-Griffin/XL-Judge-LLM",
   "activation_function": "gelu",
   "architectures": [
-    "GPT2LMHeadModel"
   ],
   "batch_size": 32,
   "dropout": 0.1,
@@ -17,6 +17,7 @@
     "3": "LABEL_3",
     "4": "LABEL_4"
   },
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -26,7 +27,7 @@
   },
   "learning_rate": 5e-05,
   "max_len": 512,
-  "model_type": "gpt2",
   "n_head": 12,
   "n_layer": 12,
   "torch_dtype": "float32",

 {
+  "_name_or_path": "Wonder-Griffin/judge-xl-model",
   "activation_function": "gelu",
   "architectures": [
+    "JudgeXL"
   ],
   "batch_size": 32,
   "dropout": 0.1,
     "3": "LABEL_3",
     "4": "LABEL_4"
   },
+  "is_decoder": true,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
   },
   "learning_rate": 5e-05,
   "max_len": 512,
+  "model_type": "judge-xl",
   "n_head": 12,
   "n_layer": 12,
   "torch_dtype": "float32",