Text Generation
Transformers
Safetensors
Italian
gpt2
DAC
data-ai
DATA-AI
transformer
experimental
text-generation-inference
Instructions to use Mattimax/microDAC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mattimax/microDAC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Mattimax/microDAC")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Mattimax/microDAC") model = AutoModelForCausalLM.from_pretrained("Mattimax/microDAC", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Mattimax/microDAC with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mattimax/microDAC" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Mattimax/microDAC", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Mattimax/microDAC
- SGLang
How to use Mattimax/microDAC 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 "Mattimax/microDAC" \ --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": "Mattimax/microDAC", "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 "Mattimax/microDAC" \ --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": "Mattimax/microDAC", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Mattimax/microDAC with Docker Model Runner:
docker model run hf.co/Mattimax/microDAC
Update README.md
Browse files
README.md
CHANGED
|
@@ -87,18 +87,6 @@ I token dell’utente vengono mascherati con `-100` nei label per evitare che il
|
|
| 87 |
|
| 88 |
---
|
| 89 |
|
| 90 |
-
## 🧩 File e struttura
|
| 91 |
-
|
| 92 |
-
| File / Cartella | Descrizione |
|
| 93 |
-
|-------------------------|--------------------------------------------------|
|
| 94 |
-
| `train_microDAC.py` | Script completo di training |
|
| 95 |
-
| `microDAC_dataset.jsonl`| Dataset in formato JSONL |
|
| 96 |
-
| `tokenizer_microDAC/` | Tokenizer BPE addestrato |
|
| 97 |
-
| `./microDAC-40M/` | Output training + checkpoint |
|
| 98 |
-
| `./microDAC-40M/final/` | Modello finale e tokenizer salvati |
|
| 99 |
-
|
| 100 |
-
---
|
| 101 |
-
|
| 102 |
## 🖥️ Compatibilità e ambiente
|
| 103 |
|
| 104 |
- Sistema operativo: Windows (con `freeze_support`)
|
|
|
|
| 87 |
|
| 88 |
---
|
| 89 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
## 🖥️ Compatibilità e ambiente
|
| 91 |
|
| 92 |
- Sistema operativo: Windows (con `freeze_support`)
|