Instructions to use basically-experimental/Pebble-50M-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basically-experimental/Pebble-50M-beta with Transformers:

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

pipe = pipeline("text-generation", model="basically-experimental/Pebble-50M-beta", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("basically-experimental/Pebble-50M-beta", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use basically-experimental/Pebble-50M-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "basically-experimental/Pebble-50M-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basically-experimental/Pebble-50M-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/basically-experimental/Pebble-50M-beta

SGLang

How to use basically-experimental/Pebble-50M-beta 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 "basically-experimental/Pebble-50M-beta" \
    --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": "basically-experimental/Pebble-50M-beta",
		"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 "basically-experimental/Pebble-50M-beta" \
        --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": "basically-experimental/Pebble-50M-beta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use basically-experimental/Pebble-50M-beta with Docker Model Runner:
```
docker model run hf.co/basically-experimental/Pebble-50M-beta
```

Pebble-50M-beta

Pebble-50M-beta is an experimental 50M-parameter language model designed to test how a larger Pebble architecture performs with a 16,384-token vocabulary and 16,384-token context window.

Despite having roughly twice the parameters of Pebble-25M, Pebble-50M-beta underperformed Pebble-25M and, on some evaluations, Pebble-10M. This model is therefore primarily useful as an experimental result rather than as the strongest Pebble model.

Model Details

Architecture: Hybrid Mamba2 / Transformer
Block Pattern: 3 Mamba2 blocks : 1 Attention block (repeating)
Parameters: ~49,334,448 (50M)
Hidden Dimension: 768
Layers: 8 (6 Mamba2, 2 Attention)
Vocab Size: 16,384 (Custom Byte-Level BPE)
Context Length: 16,384
Training Tokens: ~~25,000,000,000 (~~25 Billion)
Optimizer: Muon (for 2D hidden weights) + AdamW (for embeddings, norms, and scalars)
Precision: fp32 master weights with bf16 autocast

Dataset Sources

The model was trained on a 25B-token subset of the following datasets:

Dataset	Token Allocation	Share
FineWeb-Edu	7.50 billion	30%
DCLM	5.00 billion	20%
Cosmopedia-v2	3.75 billion	15%
FineMath-4+	3.75 billion	15%
FinePhrase	3.00 billion	12%
NPset	2.00 billion	8%
Total	25.00 billion	100%

Benchmarks

The original benchmark logs for this model were lost, so exact evaluation results are unavailable.

Qualitatively, Pebble-50M-beta underperformed Pebble-25M and, on some evaluations, Pebble-10M.

Usage

Pebble-50M-beta does not require the mamba-ssm library and is intended to be usable with standard PyTorch-based inference implementations.

It may run on CUDA GPUs, AMD GPUs, Intel GPUs, and CPUs depending on the inference framework and available hardware acceleration.

Status

This is a beta/experimental model. It is primarily intended for research and experimentation with the Pebble architecture.

License

Apache 2.0

Downloads last month: 109

Safetensors

Model size

61.9M params

Tensor type

F32