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

Libraries

How to use appvoid/a-cool-model with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("appvoid/a-cool-model")
model = AutoModelForCausalLM.from_pretrained("appvoid/a-cool-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 Settings

vLLM

How to use appvoid/a-cool-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "appvoid/a-cool-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": "appvoid/a-cool-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/appvoid/a-cool-model

SGLang

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

Docker Model Runner
How to use appvoid/a-cool-model with Docker Model Runner:
```
docker model run hf.co/appvoid/a-cool-model
```

this is just a run i did recently that i think is good and most people will like given its size.

it might be better at instruction following for text editing tasks than most 0.5b models, use it with precaution though.

it behaves super weird but when it works it actually surpasses even 1b models, super weird stuff happening here.

all i can say is that is sota for some things and super bad at others.

you can test it against lfm2.5 350m which is the base model and tell me which one you like more.

dataset is wip for a commercial project i have, more details soon. (i hope)

Downloads last month: 25

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for appvoid/a-cool-model

Base model

appvoid/v118-dpo-round-01

Finetuned

(1)

this model