Instructions to use BeardedMonster/SabiYarn-125M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeardedMonster/SabiYarn-125M with Transformers:

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

pipe = pipeline("text-generation", model="BeardedMonster/SabiYarn-125M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BeardedMonster/SabiYarn-125M", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BeardedMonster/SabiYarn-125M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeardedMonster/SabiYarn-125M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BeardedMonster/SabiYarn-125M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BeardedMonster/SabiYarn-125M

SGLang

How to use BeardedMonster/SabiYarn-125M 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 "BeardedMonster/SabiYarn-125M" \
    --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": "BeardedMonster/SabiYarn-125M",
		"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 "BeardedMonster/SabiYarn-125M" \
        --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": "BeardedMonster/SabiYarn-125M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BeardedMonster/SabiYarn-125M with Docker Model Runner:
```
docker model run hf.co/BeardedMonster/SabiYarn-125M
```

Downstream Issues Due to Inference-time Optimization in Model Forward

by theyorubayesian - opened Jan 6, 2025

Discussion

theyorubayesian

Jan 6, 2025

There's an optimization in the model forward that limits the logits returned to the last timestep (https://huggingface.co/BeardedMonster/SabiYarn-125M/blob/main/pretrained_model.py#L196). This causes issues during likelihood-based evaluations where the logits need to be processed.

BeardedMonster

Owner Jan 7, 2025

I will work sort it out as soon as i can. Thank you.

BeardedMonster changed discussion status to closed Jan 7, 2025

BeardedMonster

Owner Jan 7, 2025

It has been fixed. Logits for all time steps should be returned now.

BeardedMonster changed discussion status to open Jan 7, 2025

BeardedMonster changed discussion status to closed Jan 7, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment