Instructions to use sofieshus/reuters-falcon-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sofieshus/reuters-falcon-qlora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-7b")
model = PeftModel.from_pretrained(base_model, "sofieshus/reuters-falcon-qlora")

Transformers

How to use sofieshus/reuters-falcon-qlora with Transformers:

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

pipe = pipeline("text-generation", model="sofieshus/reuters-falcon-qlora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sofieshus/reuters-falcon-qlora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sofieshus/reuters-falcon-qlora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sofieshus/reuters-falcon-qlora

SGLang

How to use sofieshus/reuters-falcon-qlora 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 "sofieshus/reuters-falcon-qlora" \
    --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": "sofieshus/reuters-falcon-qlora",
		"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 "sofieshus/reuters-falcon-qlora" \
        --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": "sofieshus/reuters-falcon-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sofieshus/reuters-falcon-qlora with Docker Model Runner:
```
docker model run hf.co/sofieshus/reuters-falcon-qlora
```

reuters-falcon-qlora

This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.0672

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: 0.0005
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.2245	1.0	16	2.0672

Framework versions

PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.10.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 4

Model tree for sofieshus/reuters-falcon-qlora

Base model

tiiuae/falcon-7b

Adapter

(290)

this model