Instructions to use davelotito/donut_experiment_bayesian_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davelotito/donut_experiment_bayesian_3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="davelotito/donut_experiment_bayesian_3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("davelotito/donut_experiment_bayesian_3")
model = AutoModelForMultimodalLM.from_pretrained("davelotito/donut_experiment_bayesian_3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use davelotito/donut_experiment_bayesian_3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davelotito/donut_experiment_bayesian_3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davelotito/donut_experiment_bayesian_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/davelotito/donut_experiment_bayesian_3

SGLang

How to use davelotito/donut_experiment_bayesian_3 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 "davelotito/donut_experiment_bayesian_3" \
    --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": "davelotito/donut_experiment_bayesian_3",
		"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 "davelotito/donut_experiment_bayesian_3" \
        --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": "davelotito/donut_experiment_bayesian_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use davelotito/donut_experiment_bayesian_3 with Docker Model Runner:
```
docker model run hf.co/davelotito/donut_experiment_bayesian_3
```

davelotito commited on May 20, 2024

Commit

2f57fbb

verified ·

1 Parent(s): 9d28145

Training in progress, epoch 2

Browse files

Files changed (3) hide show

metrics.jsonl +1 -0
model.safetensors +1 -1
runs/May20_14-40-15_ip-172-16-167-107.ec2.internal/events.out.tfevents.1716216015.ip-172-16-167-107.ec2.internal.15611.0 +2 -2

metrics.jsonl CHANGED Viewed

	@@ -1 +1,2 @@
1	{"eval_loss": 0.8003033995628357, "eval_bleu": 0.03888514151556339, "eval_precisions": [0.6645021645021645, 0.5061728395061729, 0.4396551724137931, 0.3745704467353952], "eval_brevity_penalty": 0.0801536770551255, "eval_length_ratio": 0.28378378378378377, "eval_translation_length": 462, "eval_reference_length": 1628, "eval_cer": 0.7748649914772914, "eval_wer": 0.8614735352562218, "eval_runtime": 181.4627, "eval_samples_per_second": 0.314, "eval_steps_per_second": 0.314, "epoch": 1.0}


1	{"eval_loss": 0.8003033995628357, "eval_bleu": 0.03888514151556339, "eval_precisions": [0.6645021645021645, 0.5061728395061729, 0.4396551724137931, 0.3745704467353952], "eval_brevity_penalty": 0.0801536770551255, "eval_length_ratio": 0.28378378378378377, "eval_translation_length": 462, "eval_reference_length": 1628, "eval_cer": 0.7748649914772914, "eval_wer": 0.8614735352562218, "eval_runtime": 181.4627, "eval_samples_per_second": 0.314, "eval_steps_per_second": 0.314, "epoch": 1.0}
2	+ {"eval_loss": 0.6344355940818787, "eval_bleu": 0.052030851722171666, "eval_precisions": [0.7112970711297071, 0.5890736342042755, 0.5357142857142857, 0.4935064935064935], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.7785648277776906, "eval_wer": 0.8579665473564559, "eval_runtime": 71.1013, "eval_samples_per_second": 0.802, "eval_steps_per_second": 0.802, "epoch": 2.0}

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df18bd50aa2caaa17b33a339b709535c5e5bbf6f99c6ff8012d14cacc55680e
 size 809103512

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd30310cb9f1b7aceb74c0ecb7f2c7fa9ae1977bbf1adae54b2702de636d5656
 size 809103512

runs/May20_14-40-15_ip-172-16-167-107.ec2.internal/events.out.tfevents.1716216015.ip-172-16-167-107.ec2.internal.15611.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ac8b6297b9ad1ce5788c65eda58f43a451ee82684fbb5cc40abaa163a2171c
-size 10275

 version https://git-lfs.github.com/spec/v1
+oid sha256:80fea50ee02ced9772dbf6fa38f2906da0f269fdd4a4041233490c18cd250f55
+size 11912