Instructions to use m-a-p/Kun-LabelModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m-a-p/Kun-LabelModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="m-a-p/Kun-LabelModel")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("m-a-p/Kun-LabelModel") model = AutoModelForCausalLM.from_pretrained("m-a-p/Kun-LabelModel") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use m-a-p/Kun-LabelModel with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "m-a-p/Kun-LabelModel" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "m-a-p/Kun-LabelModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/m-a-p/Kun-LabelModel
- SGLang
How to use m-a-p/Kun-LabelModel 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 "m-a-p/Kun-LabelModel" \ --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": "m-a-p/Kun-LabelModel", "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 "m-a-p/Kun-LabelModel" \ --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": "m-a-p/Kun-LabelModel", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use m-a-p/Kun-LabelModel with Docker Model Runner:
docker model run hf.co/m-a-p/Kun-LabelModel
Upload all_results.json with huggingface_hub
Browse files- all_results.json +10 -0
all_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.76,
|
| 3 |
+
"train_loss": 1.082658023883899,
|
| 4 |
+
"train_output_tokens": 1298884,
|
| 5 |
+
"train_runtime": 22627.0931,
|
| 6 |
+
"train_samples": 26000,
|
| 7 |
+
"train_samples_per_second": 4.596,
|
| 8 |
+
"train_steps_per_second": 0.002,
|
| 9 |
+
"train_total_tokens": 9672793
|
| 10 |
+
}
|