Instructions to use Finisha-F-scratch/Gheya-63M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Finisha-F-scratch/Gheya-63M with Transformers:

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

pipe = pipeline("text-generation", model="Finisha-F-scratch/Gheya-63M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/Gheya-63M")
model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/Gheya-63M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Finisha-F-scratch/Gheya-63M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Finisha-F-scratch/Gheya-63M"
# 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/Gheya-63M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Finisha-F-scratch/Gheya-63M

SGLang

How to use Finisha-F-scratch/Gheya-63M 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/Gheya-63M" \
    --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/Gheya-63M",
		"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/Gheya-63M" \
        --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/Gheya-63M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Finisha-F-scratch/Gheya-63M with Docker Model Runner:
```
docker model run hf.co/Finisha-F-scratch/Gheya-63M
```

Commentaire

by Nora-006 - opened Jan 23

Discussion

Nora-006

Jan 23

Ce LLM est un peu nulle ,
Voici sa liste de défauts 😀

il y a d'énormes problèmes de syntaxes, il ne sais pas formé des mots français cohérents,
Quand il sort des vrais mots, c'est toujours les mêmes
il boucle.
il écrit d'une façon hyper bizzare, genre on dirait un robot de merde qui hésite sur ses mots.

Voilà merci!
C'est que mon avis,
Mais tu devrait affiné des modèles existants au lieu de faire from scratch
Le from scratch n'est pas pour toi.

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