Instructions to use Conlanger-LLM-CLEM/Sorie with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Conlanger-LLM-CLEM/Sorie with Transformers:

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

pipe = pipeline("text-generation", model="Conlanger-LLM-CLEM/Sorie", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Conlanger-LLM-CLEM/Sorie", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Conlanger-LLM-CLEM/Sorie with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Conlanger-LLM-CLEM/Sorie

SGLang

How to use Conlanger-LLM-CLEM/Sorie 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 "Conlanger-LLM-CLEM/Sorie" \
    --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": "Conlanger-LLM-CLEM/Sorie",
		"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 "Conlanger-LLM-CLEM/Sorie" \
        --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": "Conlanger-LLM-CLEM/Sorie",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Conlanger-LLM-CLEM/Sorie with Docker Model Runner:
```
docker model run hf.co/Conlanger-LLM-CLEM/Sorie
```

Clem27-Assistants commited on Mar 26

Commit

33bc31c

verified ·

1 Parent(s): ff24cf1

Update README.md

Browse files

Files changed (1) hide show

README.md +22 -1

README.md CHANGED Viewed

@@ -10,4 +10,25 @@ model-index:
 license: bigscience-openrail-m
 language:
 - fr
----

 license: bigscience-openrail-m
 language:
 - fr
+---
+# 🌟 Sorie-0.5B : Documentation Officielle
+![sorie](http://www.image-heberg.fr/files/1774555992455317236.webp)
+Bienvenue dans la documentation de Sorie, un LLM innovant conçu pour l'efficacité et la performance. Développé entièrement from scratch par Clem, Sorie repose sur l'architecture propriétaire SoraForSLM.
+# 📊 Fiche Technique
+| Caractéristique | Détails |
+|---|---|
+| Nom du Modèle | Sorie-0.5B |
+| Version | 1.0.0 |
+| Développeur | Clem |
+| Type | Décodeur-uniquement (Causal LM) |
+| Nombre de paramètres | ~500 millions |
+| Format | PyTorch / Safetensors |
+ # 💕 Sorie
+> "Sorie est le fruit d'une exploration passionnée sur l'optimisation des architectures de langage. L'objectif était de prouver qu'un modèle de 0.5B peut être à la fois intelligent et extrêmement agile." — Clem
+>
+# 📜 Licence
+Sorie est distribuée sous licence artistique.