Instructions to use stage-babylm/llama-256-12L-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stage-babylm/llama-256-12L-qa with Transformers:

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

pipe = pipeline("text-generation", model="stage-babylm/llama-256-12L-qa")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stage-babylm/llama-256-12L-qa")
model = AutoModelForCausalLM.from_pretrained("stage-babylm/llama-256-12L-qa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stage-babylm/llama-256-12L-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stage-babylm/llama-256-12L-qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stage-babylm/llama-256-12L-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stage-babylm/llama-256-12L-qa

SGLang

How to use stage-babylm/llama-256-12L-qa 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 "stage-babylm/llama-256-12L-qa" \
    --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": "stage-babylm/llama-256-12L-qa",
		"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 "stage-babylm/llama-256-12L-qa" \
        --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": "stage-babylm/llama-256-12L-qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stage-babylm/llama-256-12L-qa with Docker Model Runner:
```
docker model run hf.co/stage-babylm/llama-256-12L-qa
```

llama-256-12L-qa

This model is a fine-tuned version of stage-babylm/llama-256-12L on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.7426

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.6367	0.1507	171	2.5935
2.0299	0.3013	342	1.9835
1.8834	0.4520	513	1.8715
1.8843	0.6026	684	1.8319
1.7929	0.7533	855	1.8088
1.8340	0.9040	1026	1.7920
1.6984	1.0546	1197	1.7805
1.7795	1.2053	1368	1.7718
1.7848	1.3559	1539	1.7657
1.7373	1.5066	1710	1.7593
1.7183	1.6573	1881	1.7548
1.7889	1.8079	2052	1.7509
1.6819	1.9586	2223	1.7478
1.7535	2.1093	2394	1.7460
1.6669	2.2599	2565	1.7448
1.7614	2.4106	2736	1.7437
1.6935	2.5612	2907	1.7431
1.7186	2.7119	3078	1.7428
1.6719	2.8626	3249	1.7426
1.6835	3.0	3405	1.7426

Framework versions

Transformers 5.14.1
Pytorch 2.13.0+cu130
Datasets 5.0.0
Tokenizers 0.22.2

Downloads last month: 153

Safetensors

Model size

9.95M params

Tensor type

F32

Model tree for stage-babylm/llama-256-12L-qa

Base model

stage-babylm/llama-256-12L

Finetuned

(2)

this model

stage-babylm
/

llama-256-12L-qa

llama-256-12L-qa

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for stage-babylm/llama-256-12L-qa

Space using stage-babylm/llama-256-12L-qa 1