From scratch
Collection
Finisha SLM ✨ • 87 items • Updated
How to use Finisha-F-scratch/Gheya-111M with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Finisha-F-scratch/Gheya-111M") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Finisha-F-scratch/Gheya-111M")
model = AutoModelForCausalLM.from_pretrained("Finisha-F-scratch/Gheya-111M")How to use Finisha-F-scratch/Gheya-111M with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Finisha-F-scratch/Gheya-111M"
# 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-111M",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Finisha-F-scratch/Gheya-111M
How to use Finisha-F-scratch/Gheya-111M with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Finisha-F-scratch/Gheya-111M" \
--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-111M",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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-111M" \
--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-111M",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Finisha-F-scratch/Gheya-111M with Docker Model Runner:
docker model run hf.co/Finisha-F-scratch/Gheya-111M
Gheya-111M n'est pas faite pour les longs discours robotiques. Elle excelle dans :
Le modèle ne souffre pas de "bugs", il déploie sa propre logique :
"Gheya-111M ne parle pas comme un humain. Elle parle comme une IA qui sait qu'elle est une création de mots." 🔗🤏