Instructions to use BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny with Transformers:

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

pipe = pipeline("text-generation", model="BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny

SGLang

How to use BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny 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 "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny" \
    --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": "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny",
		"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 "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny" \
        --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": "BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny with Docker Model Runner:
```
docker model run hf.co/BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny
```

falcon-7b-ft-mc4_nl_cleaned_tiny

This model is a fine-tuned version of tiiuae/falcon-7b on the yhavinga/mc4_nl_cleaned dataset (tiny partition) on a context of 2048 tokens. See the original tiiuae/falcon-7b for more information, intended use, and biases.

Intended uses & limitations

This model is intended as a (poor) baseline for Dutch generative LLMs. It by no means aims to provide SOTA performance and is specifically intended for research purposes.

Importantly, the original Falcon 7B model was only trained on English and French. Therefore, Dutch generations should be taken with a massive grain of salt. I wanted to see if the performance would be reasonable after finetuning this model on a Dutch dataset. I find that it is okay but not great. It's especially not coherent.

Training and evaluation data

Trained on the yhavinga/mc4_nl_cleaned dataset (tiny partition) for one epoch. The canonical validation split was not used but instead 5% of train was used as validation.

At 2048 tokens context length, the training set was around 2M (2,008,858) samples, and the model was trained for 1 epoch. That means that the model was trained for around 4B Dutch tokens (2048 * 2008858 = 4.114.141.184).

Training procedure

Trained with LoRA targetting ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h'] in 4 bit and merged before upload. The adapters are in the adapters branch.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 12
eval_batch_size: 24
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 6
total_train_batch_size: 1152
total_eval_batch_size: 384
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.6094	0.1	170	2.5980
2.4503	0.19	340	2.4405
2.3243	0.29	510	2.3428
2.2822	0.39	680	2.2752
2.238	0.49	850	2.2248
2.2015	0.58	1020	2.1865
2.1678	0.68	1190	2.1560
2.1301	0.78	1360	2.1312
2.1161	0.88	1530	2.1112
2.0997	0.97	1700	2.0928

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.13.1
Tokenizers 0.13.3

Downloads last month: 12

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny

Base model

tiiuae/falcon-7b

Finetuned

(46)

this model

Dataset used to train BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny

Collection including BramVanroy/falcon-7b-ft-mc4_nl_cleaned_tiny

Llama 2 & Falcon finetunes

Collection

Older finetunes - not recommended! • 10 items • Updated Apr 10 • 1