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

Libraries

How to use BEGADE/model with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEGADE/model")
model = AutoModelForCausalLM.from_pretrained("BEGADE/model")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BEGADE/model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BEGADE/model

SGLang

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

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

BEGADE commited on Sep 10, 2024

Commit

c0efa47

verified ·

1 Parent(s): f086ba6

Training in progress, step 2500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Sep10_01-12-14_9140fd6908f0/events.out.tfevents.1725930807.9140fd6908f0.228.1 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c9182e56136d4a4fb60809bf6d4e664218e8601688dccdb4b1bb33cb414c76
 size 497780352

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa1bcb38ef467c8d601f49cbac4feef28096102de7633fe3c7c7cc055cdaab05
 size 497780352

runs/Sep10_01-12-14_9140fd6908f0/events.out.tfevents.1725930807.9140fd6908f0.228.1 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2691da0e68c6d5b9893d8515c9f3df4a703d18fe9fb64df9ba06c0e4b1a92f1
-size 9762

 version https://git-lfs.github.com/spec/v1
+oid sha256:24947b94d5d33059dbfe5d9189a2c7879126e27e751a3328900e7a1d56213275
+size 10817