Instructions to use WillisBack/gemma-Summarizer-2b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WillisBack/gemma-Summarizer-2b-it with Transformers:

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

pipe = pipeline("text-generation", model="WillisBack/gemma-Summarizer-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WillisBack/gemma-Summarizer-2b-it")
model = AutoModelForCausalLM.from_pretrained("WillisBack/gemma-Summarizer-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WillisBack/gemma-Summarizer-2b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WillisBack/gemma-Summarizer-2b-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WillisBack/gemma-Summarizer-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WillisBack/gemma-Summarizer-2b-it

SGLang

How to use WillisBack/gemma-Summarizer-2b-it 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 "WillisBack/gemma-Summarizer-2b-it" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WillisBack/gemma-Summarizer-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "WillisBack/gemma-Summarizer-2b-it" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WillisBack/gemma-Summarizer-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use WillisBack/gemma-Summarizer-2b-it with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for WillisBack/gemma-Summarizer-2b-it to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for WillisBack/gemma-Summarizer-2b-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WillisBack/gemma-Summarizer-2b-it to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="WillisBack/gemma-Summarizer-2b-it",
    max_seq_length=2048,
)

Docker Model Runner
How to use WillisBack/gemma-Summarizer-2b-it with Docker Model Runner:
```
docker model run hf.co/WillisBack/gemma-Summarizer-2b-it
```

Uploaded as 16bit model

Developed by: Labagaite
License: apache-2.0
Finetuned from model : unsloth/gemma-2b-it-bnb-4bit

Training Logs

Traning metrics

Evaluation score

Évaluation du rapport généré par le modèle unsloth/gemma-2b-it-bnb-4bit :

Performance de la structuration du rapport : 6/10
- Le rapport est bien structuré en chapitres distincts, mais certains points pourraient être mieux développés et organisés.
Qualité du langage : 7/10
- Le langage utilisé est formel et professionnel, mais il manque parfois de fluidité et de clarté dans l'expression des idées.
Cohérence : 6/10
- La cohérence entre les différents chapitres est présente, mais il y a des transitions abruptes et des lacunes dans certaines explications.

Évaluation du rapport généré par le modèle gemma-Summarizer-2b-it-bnb-4bit :

Performance de la structuration du rapport : 8/10
- Le rapport est bien structuré en sections claires et précises, facilitant la lecture et la compréhension.
Qualité du langage : 8/10
- Le langage utilisé est riche et varié, offrant une lecture agréable et captivante pour le lecteur.
Cohérence : 7/10
- La cohérence entre les différentes parties du rapport est bonne, mais certaines transitions pourraient être améliorées pour une meilleure fluidité.

Score global :

Modèle unsloth/gemma-2b-it-bnb-4bit : 6.3/10
Modèle gemma-Summarizer-2b-it-bnb-4bit : 7.7/10

Conclusion :

Le modèle gemma-Summarizer-2b-it-bnb-4bit obtient un score global plus élevé que le modèle unsloth/gemma-2b-it-bnb-4bit en raison de sa meilleure structuration, de la qualité supérieure du langage utilisé et d'une cohérence globale plus solide. Le rapport généré par le modèle gemma-Summarizer-2b-it-bnb-4bit est plus complet, captivant et bien organisé, ce qui en fait un choix préférable pour la génération de rapports détaillés et professionnels. Evaluation report and scoring

Wandb logs

You can view the training logs .

Training details

training data

Dataset : fr-summarizer-dataset
Data-size : 7.65 MB
train : 1.97k rows
validation : 440 rows
roles : user , assistant
Format chatml "role": "role", "content": "content", "user": "user", "assistant": "assistant"
*French audio podcast transcription*

Project details

Fine-tuned on French audio podcast transcription data for summarization task. As a result, the model is able to summarize French audio podcast transcription data. The model will be used for an AI application: Report Maker wich is a powerful tool designed to automate the process of transcribing and summarizing meetings. It leverages state-of-the-art machine learning models to provide detailed and accurate reports.

This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library. This gemma was trained with LLM summarizer trainer LLM summarizer trainer