Instructions to use MisterAI/ALMANACH_CamemBERT_Agent001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MisterAI/ALMANACH_CamemBERT_Agent001 with Transformers:

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

pipe = pipeline("text-generation", model="MisterAI/ALMANACH_CamemBERT_Agent001")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MisterAI/ALMANACH_CamemBERT_Agent001")
model = AutoModelForCausalLM.from_pretrained("MisterAI/ALMANACH_CamemBERT_Agent001", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MisterAI/ALMANACH_CamemBERT_Agent001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MisterAI/ALMANACH_CamemBERT_Agent001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MisterAI/ALMANACH_CamemBERT_Agent001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MisterAI/ALMANACH_CamemBERT_Agent001

SGLang

How to use MisterAI/ALMANACH_CamemBERT_Agent001 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 "MisterAI/ALMANACH_CamemBERT_Agent001" \
    --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": "MisterAI/ALMANACH_CamemBERT_Agent001",
		"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 "MisterAI/ALMANACH_CamemBERT_Agent001" \
        --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": "MisterAI/ALMANACH_CamemBERT_Agent001",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MisterAI/ALMANACH_CamemBERT_Agent001 with Docker Model Runner:
```
docker model run hf.co/MisterAI/ALMANACH_CamemBERT_Agent001
```

Basé Sur Le Modèle Originale :

Almanach/camembert-base :

"A Tasty French Language Model"

Lien : https://huggingface.co/almanach/camembert-base

Pre-trained models by almanach/camembert-base

https://huggingface.co/almanach/camembert-base/blob/main/README.md#pre-trained-models

Model	#params	Arch.	Training data
`camembert-base`	110M	Base	OSCAR (138 GB of text)
`camembert/camembert-large`	335M	Large	CCNet (135 GB of text)
`camembert/camembert-base-ccnet`	110M	Base	CCNet (135 GB of text)
`camembert/camembert-base-wikipedia-4gb`	110M	Base	Wikipedia (4 GB of text)
`camembert/camembert-base-oscar-4gb`	110M	Base	Subsample of OSCAR (4 GB of text)
`camembert/camembert-base-ccnet-4gb`	110M	Base	Subsample of CCNet (4 GB of text)

Fine-Tunning by MisterAI/ALMANACH_CamemBERT_Agent001

Testing Training/FineTunning For Now >:)

Model	#params	Arch.	Training data
`MisterAI/ALMANACH_CamemBERT_Agent001` based on `camembert-base`	110M	Base	MisterAI/SimpleSmallFrenchQA (50 KB of text)

If you use our work, please cite:

@inproceedings{martin2020camembert, title={CamemBERT: a Tasty French Language Model}, author={Martin, Louis and Muller, Benjamin and Su{'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {'E}ric Villemonte and Seddah, Djam{'e} and Sagot, Beno{^\i}t}, booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, year={2020} }

Downloads last month: 3

Safetensors

Model size

0.1B params

Tensor type

F32

MisterAI
/

ALMANACH_CamemBERT_Agent001