Instructions to use malikali/CEFR-Aligned-LM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use malikali/CEFR-Aligned-LM with Transformers:

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

pipe = pipeline("text-generation", model="malikali/CEFR-Aligned-LM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("malikali/CEFR-Aligned-LM")
model = AutoModelForCausalLM.from_pretrained("malikali/CEFR-Aligned-LM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use malikali/CEFR-Aligned-LM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/malikali/CEFR-Aligned-LM

SGLang

How to use malikali/CEFR-Aligned-LM 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 "malikali/CEFR-Aligned-LM" \
    --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": "malikali/CEFR-Aligned-LM",
		"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 "malikali/CEFR-Aligned-LM" \
        --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": "malikali/CEFR-Aligned-LM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use malikali/CEFR-Aligned-LM with Docker Model Runner:
```
docker model run hf.co/malikali/CEFR-Aligned-LM
```

CEFF-Aligned Language Model (CaLM)

This is a model card for the CEFF-Aligned Language Model (CaLM) from the paper: From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

Paper: https://aclanthology.org/2024.findings-acl.926
Arxiv: https://arxiv.org/abs/2406.03030
Github: https://github.com/malik-ali/tarzan2tolkien

Prompt Template

The model text template looks like

<<Summary>>: {summary}
<<CEFR>>: {cefr}
<<Story>>:
{story}
<</Story>>

where you replace {summary} with the summary of the desired story to generate and {cefr} with the desired CEFR level is one of ["A1", "A2", "B1", "B2", "C1", "C2"].

To generate, you can add the summary and target CEFR level and just start generating after the <<Story>>:\n . See the Github repo for examples.

Downloads last month: 53

Model tree for malikali/CEFR-Aligned-LM

Base model

meta-llama/Llama-2-7b-hf

Finetuned

(981)

this model

Paper for malikali/CEFR-Aligned-LM

From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

Paper • 2406.03030 • Published Jun 5, 2024