Instructions to use Multi-Domain-Expert-Learning/all_layers_all_domains with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/all_layers_all_domains with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/all_layers_all_domains")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/all_layers_all_domains")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/all_layers_all_domains")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/all_layers_all_domains with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/all_layers_all_domains

SGLang

How to use Multi-Domain-Expert-Learning/all_layers_all_domains 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 "Multi-Domain-Expert-Learning/all_layers_all_domains" \
    --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": "Multi-Domain-Expert-Learning/all_layers_all_domains",
		"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 "Multi-Domain-Expert-Learning/all_layers_all_domains" \
        --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": "Multi-Domain-Expert-Learning/all_layers_all_domains",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/all_layers_all_domains with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/all_layers_all_domains
```

jordiclive commited on May 7, 2023

Commit

6f8a8db

1 Parent(s): 4f209d8

update model card README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -33,13 +33,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 32
-- eval_batch_size: 32
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 2048
-- total_eval_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1

 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1