Instructions to use kevin510/friday with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kevin510/friday with Transformers:

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

pipe = pipeline("text-generation", model="kevin510/friday", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("kevin510/friday", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kevin510/friday with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kevin510/friday"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kevin510/friday",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kevin510/friday

SGLang

How to use kevin510/friday 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 "kevin510/friday" \
    --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": "kevin510/friday",
		"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 "kevin510/friday" \
        --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": "kevin510/friday",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kevin510/friday with Docker Model Runner:
```
docker model run hf.co/kevin510/friday
```

kevin510 commited on Jun 6, 2025

Commit

6019dc7

verified ·

1 Parent(s): 3d0825c

Update modeling_friday.py

Browse files

Files changed (1) hide show

modeling_friday.py +3 -0

modeling_friday.py CHANGED Viewed

@@ -689,6 +689,9 @@ import PIL
 from transformers import AutoTokenizer, AutoConfig
 from transformers.modeling_outputs import CausalLMOutputWithPast
 DEFAULT_CFG_SPECIAL_TOKENS = {
     "image_token_id": 200029,

 from transformers import AutoTokenizer, AutoConfig
 from transformers.modeling_outputs import CausalLMOutputWithPast
+from .configuration_phi3 import Phi3Config
+from .modeling_phi3 import Phi3Model, Phi3ForCausalLM
 DEFAULT_CFG_SPECIAL_TOKENS = {
     "image_token_id": 200029,