Downloads · 30 days
20
29% of all-time downloads
Eclairmania/amadeus-merged
amadeus-merged is a text generation model from Eclairmania. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Modèle basé sur Phi-3-mini-4k-instruct, fine-tuné pour des conversations en français avec un style scientifique.
Downloads · 30 days
20
29% of all-time downloads
All-time downloads
70
Public
Parameters
3.8B
7.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.6 GB · 100%
From the Hugging Face model README
Modèle basé sur Phi-3-mini-4k-instruct, fine-tuné pour des conversations en français avec un style scientifique.
Le modèle utilise le format Phi-3 :
<|user|>
Votre message<|end|>
<|assistant|>
from huggingface_hub import InferenceClient
client = InferenceClient("Eclairmania/amadeus-merged", token="votre_token")
response = client.text_generation(
"<|user|>\nBonjour<|end|>\n<|assistant|>\n",
max_new_tokens=150
)
print(response)
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Eclairmania/amadeus-merged")
tokenizer = AutoTokenizer.from_pretrained("Eclairmania/amadeus-merged")
prompt = "<|user|>\nBonjour<|end|>\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))