Instructions to use opencompass/CompassJudger-1-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use opencompass/CompassJudger-1-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="opencompass/CompassJudger-1-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("opencompass/CompassJudger-1-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("opencompass/CompassJudger-1-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use opencompass/CompassJudger-1-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "opencompass/CompassJudger-1-32B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "opencompass/CompassJudger-1-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/opencompass/CompassJudger-1-32B-Instruct

SGLang

How to use opencompass/CompassJudger-1-32B-Instruct 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 "opencompass/CompassJudger-1-32B-Instruct" \
    --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": "opencompass/CompassJudger-1-32B-Instruct",
		"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 "opencompass/CompassJudger-1-32B-Instruct" \
        --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": "opencompass/CompassJudger-1-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use opencompass/CompassJudger-1-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/opencompass/CompassJudger-1-32B-Instruct
```

zsytony commited on Oct 22, 2024

Commit

2461a46

verified ·

1 Parent(s): deaccd3

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -7

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ base_model:
 # CompassJudger-1
 <p align="center">
-        🤗 <a href="https://huggingface.co/opencompass">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/opencompass">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="">Paper</a> &nbsp&nbsp
 <br>
 </p>
@@ -28,7 +28,7 @@ Here provides a code to show you how to load the tokenizer and model and how to
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_name = "opencompass/CompassJudger-1"
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -64,7 +64,7 @@ print(response)
 We also provide some examples for different usage situations:
-### Gneral Chat
 ```
 **Input**: Hello, can you help me to judge something?
@@ -174,7 +174,9 @@ cd opencompass
 pip install -e .
 python run.py configs/eval_judgerbench.py --mode all --reuse latest
 ```
 ## Use CompassJudger-1 to Test Subjective Datasets in OpenCompass
@@ -225,8 +227,8 @@ infer = dict(
 judge_models = [dict(
     dict(
         type=TurboMindModelwithChatTemplate,
-        abbr='CompassJudger-1-7B,
-        path='Opencompass/CompassJudger-1-7B',
         engine_config=dict(session_len=16384, max_batch_size=16, tp=1),
         gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=2048),
         max_seq_len=16384,
@@ -254,13 +256,17 @@ For more detailed subjective evaluation guidelines, please refer to: https://git
 To facilitate better comparisons within the community, we have tested the subjective performance of some models using CompassJudger-1.
 ## Citation
 ```bib
 @article{cao2024compass,
   title={CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution},
   author={Maosong Cao, Alexander Lam, Haodong Duan, Hongwei Liu, Songyang Zhang, Kai Chen},
-  journal={arXiv preprint arXiv:2410.xxxxxx},
   year={2024}
 }
 ```
@@ -270,4 +276,4 @@ To facilitate better comparisons within the community, we have tested the subjec
 - https://github.com/open-compass/opencompass
 - https://github.com/InternLM/InternLM
 - https://github.com/QwenLM/Qwen2.5
-- https://github.com/InternLM/xtuner

 # CompassJudger-1
 <p align="center">
+        🤗 <a href="https://huggingface.co/opencompass">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/organization/opencompass">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/pdf/2410.16256">Paper</a> &nbsp&nbsp | &nbsp&nbsp 🎖️ <a href="https://huggingface.co/spaces/opencompass/judgerbench_leaderboard">Leaderboard</a> &nbsp&nbsp
 <br>
 </p>
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "opencompass/CompassJudger-1-7B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
 We also provide some examples for different usage situations:
+### General Chat
 ```
 **Input**: Hello, can you help me to judge something?
 pip install -e .
 python run.py configs/eval_judgerbench.py --mode all --reuse latest
 ```
+We also provided a leaderboard for JudgerBench: https://huggingface.co/spaces/opencompass/judgerbench_leaderboard
+If you want to add your model to this leaderboard, welcome to add an issue in this Repository.
 ## Use CompassJudger-1 to Test Subjective Datasets in OpenCompass
 judge_models = [dict(
     dict(
         type=TurboMindModelwithChatTemplate,
+        abbr='CompassJudger-1-7B-Instruct',
+        path='opencompass/CompassJudger-1-7B-Instruct',
         engine_config=dict(session_len=16384, max_batch_size=16, tp=1),
         gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=2048),
         max_seq_len=16384,
 To facilitate better comparisons within the community, we have tested the subjective performance of some models using CompassJudger-1.
+See in: [https://huggingface.co/spaces/opencompass/judgerbench_leaderboard](https://huggingface.co/spaces/opencompass/compassjudger_subj_eval_leaderboard)
+If you want to add your model to this leaderboard, welcome to add an issue in this Repository.
 ## Citation
 ```bib
 @article{cao2024compass,
   title={CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution},
   author={Maosong Cao, Alexander Lam, Haodong Duan, Hongwei Liu, Songyang Zhang, Kai Chen},
+  journal={arXiv preprint arXiv:2410.16256},
   year={2024}
 }
 ```
 - https://github.com/open-compass/opencompass
 - https://github.com/InternLM/InternLM
 - https://github.com/QwenLM/Qwen2.5
+- https://github.com/InternLM/xtuner