Instructions to use haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal with Transformers:

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

pipe = pipeline("text-generation", model="haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal

SGLang

How to use haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal 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 "haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal" \
    --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": "haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal",
		"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 "haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal" \
        --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": "haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal with Docker Model Runner:
```
docker model run hf.co/haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal
```

haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal

GPT-BERT style BabyBabyLLM model for language eng.

This repository may include both main and EMA variants.

Default variant exposed to generic loaders: main

Variants Available

main

Files

model.safetensors (alias of default variant)

Configuration

{
  "attention_probs_dropout_prob": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "intermediate_size": 2560,
  "max_position_embeddings": 512,
  "position_bucket_size": 32,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "vocab_size": 16384,
  "layer_norm_eps": 1e-05
}

Tokenizer file: tokenizer_eng.json

Quick Usage

from transformers import AutoTokenizer, AutoModelForMaskedLM
model_id = 'haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal'
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForMaskedLM.from_pretrained(model_id, trust_remote_code=True)
out = model(**tok('Hello world', return_tensors='pt'))

Causal LM Wrapper

This repo includes a lightweight GPTBertForCausalLM wrapper. Generation example:

from transformers import AutoTokenizer, AutoModelForCausalLM
mid='haznitrama/babybabellm-multi_gpu-gpt_bert-eng-main-causal'
tok=AutoTokenizer.from_pretrained(mid)
model=AutoModelForCausalLM.from_pretrained(mid, trust_remote_code=True)
print(tok.decode(model.generate(**tok('Hello', return_tensors='pt'), max_new_tokens=20)[0], skip_special_tokens=True))

Notes

Converted on 2025-09-27T15:21:53.977598+00:00
Weights are the exact trained parameters; no new layers were initialized.
Requires trust_remote_code=True due to custom architecture.

Downloads last month: 16

Safetensors

Model size

0.1B params

Tensor type

I64

F32