Instructions to use jl8771/bloom3b-finetuned-pdf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jl8771/bloom3b-finetuned-pdf with Transformers:

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

pipe = pipeline("text-generation", model="jl8771/bloom3b-finetuned-pdf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jl8771/bloom3b-finetuned-pdf")
model = AutoModelForCausalLM.from_pretrained("jl8771/bloom3b-finetuned-pdf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jl8771/bloom3b-finetuned-pdf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jl8771/bloom3b-finetuned-pdf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jl8771/bloom3b-finetuned-pdf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jl8771/bloom3b-finetuned-pdf

SGLang

How to use jl8771/bloom3b-finetuned-pdf 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 "jl8771/bloom3b-finetuned-pdf" \
    --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": "jl8771/bloom3b-finetuned-pdf",
		"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 "jl8771/bloom3b-finetuned-pdf" \
        --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": "jl8771/bloom3b-finetuned-pdf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jl8771/bloom3b-finetuned-pdf with Docker Model Runner:
```
docker model run hf.co/jl8771/bloom3b-finetuned-pdf
```

bloom560m-finetuned-pdf

This model is a fine-tuned version of bigscience/bloom-3b on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.2944

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: 5e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.8015	0.89	400	3.2172
2.5565	1.77	800	3.2420
2.3949	2.66	1200	3.2944

Framework versions

Transformers 4.27.1
Pytorch 2.1.0.dev20230429+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Downloads last month: 9