Instructions to use Finisha-F-scratch/Learnia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Finisha-F-scratch/Learnia with Transformers:

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

pipe = pipeline("text-generation", model="Finisha-F-scratch/Learnia")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/Learnia")
model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/Learnia")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Finisha-F-scratch/Learnia with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Finisha-F-scratch/Learnia

SGLang

How to use Finisha-F-scratch/Learnia 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 "Finisha-F-scratch/Learnia" \
    --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": "Finisha-F-scratch/Learnia",
		"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 "Finisha-F-scratch/Learnia" \
        --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": "Finisha-F-scratch/Learnia",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Finisha-F-scratch/Learnia with Docker Model Runner:
```
docker model run hf.co/Finisha-F-scratch/Learnia
```

Commentaire avis

by Nora-006 - opened Jan 23

Discussion

Nora-006

Jan 23

Meilleur LLM.
Je le préfère 1000 fois a Gheya-63m.

Clemylia

Finisha org Jan 23

Mes LLm?

Tes qui courent qu'ils sont petits et que c'est des SLM?

Nora-006

Jan 23

Bah oui,
Mais je suis élève dans une école de développement de LLM,
nous travaillons souvent sur des modèles a peine plus gros que les tiens.
Je parle de "LLM",
car c'est le domaine : des modèles capable de générer du language.Cela ne veux pas forcément dire gros

Clemylia

Finisha org Jan 23

Vous apprenez quoi a ton "école"?

Nora-006

Jan 23

On apprend a bien affiné des modèles,
Style pythia, tiny-llama, gpt2,
on fait de la théorie sur l'entraînement et le fonctionnement,
Et des fois nos professeurs entraînent from scratch, et on doit faire le meilleur affinage de leur modèle.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment