初始化项目，由ModelHub XC社区提供模型

Model: Mattimax/DACMini-IT
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,278 @@
+---
+license: mit
+datasets:
+- Mattimax/DATA-AI_Conversation_ITA
+language:
+- it
+base_model:
+- Mattimax/DACMini
+library_name: transformers
+tags:
+- DAC
+- DATA-AI
+- data-ai
+---
+
+[![HuggingFace](https://img.shields.io/badge/HuggingFace-Mattimax-brightgreen)](https://huggingface.co/Mattimax)
+[![M.INC](https://img.shields.io/badge/M.INC-Labs-blue)](https://huggingface.co/MINC01)
+
+## ☕ Support my research
+
+[![Buy Me a Coffee](https://img.shields.io/badge/Support-Buy%20Me%20a%20Coffee-FFDD00?style=for-the-badge&logo=buymeacoffee&logoColor=black)](https://www.buymeacoffee.com/marzomattye)
+
+# Mattimax/DACMini-IT
+
+![Logo di DACMini](https://huggingface.co/Mattimax/DACMini/resolve/main/DACMini_Logo/DACMini_Logo.png)
+
+* **Autore:** [Mattimax](https://huggingface.co/Mattimax)
+* **Organizzazione:** [M.INC](https://huggingface.co/MINC01)
+* **Licenza:** MIT
+
+---
+
+## Descrizione
+
+**DACMini-IT** è un modello di linguaggio compatto e instruction tuned per **chat e dialogo in lingua italiana**.
+Basato sull’architettura **GPT-2 Small (italian adaptation)**, è progettato per essere rapido, leggero e facilmente distribuibile su dispositivi con risorse limitate.
+
+Rispetto a DACMini “base”, **DACMini-IT** è addestrato su dataset italiani conversazionali strutturati in formato *user-assistant*, ottimizzando la capacità di seguire istruzioni e gestire conversazioni multi-turno naturali.
+
+---
+
+## Dimensioni e caratteristiche tecniche
+
+* **Parametri:** 109M
+* **Architettura:** GPT-2 Small (italian adaptation)
+* **Lunghezza massima del contesto:** 512 token
+* **Numero di strati:** 12
+* **Numero di teste di attenzione:** 12
+* **Dimensione embedding:** 768
+* **Vocabolario:** ~50.000 token
+* **Quantizzazione:** supportata (8-bit / 4-bit opzionale con `bitsandbytes`)
+
+---
+
+## Dataset di addestramento
+
+Addestrato su [**Mattimax/DATA-AI_Conversation_ITA**](https://huggingface.co/datasets/Mattimax/DATA-AI_Conversation_ITA), un dataset italiano di dialoghi instruction tuned, contenente coppie *prompt-response* strutturate per favorire risposte coerenti, naturali e grammaticalmente corrette.
+
+---
+
+## Obiettivi
+
+* Chatbot in lingua italiana con capacità di seguire istruzioni.
+* Risposte concise, chiare e naturali in contesti multi-turno.
+* Applicazioni leggere o offline dove la dimensione del modello è un vincolo.
+
+---
+
+## Avvertenze e limitazioni
+
+* Modello **sperimentale**: può produrre errori logici o risposte non pertinenti.
+* Non addestrato su temi sensibili o contenuti specialistici.
+* Prestazioni limitate su conversazioni molto lunghe o prompt complessi.
+* Non destinato ad usi commerciali senza ulteriore validazione.
+
+---
+
+## Uso consigliato
+
+* Applicazioni chatbot leggere o offline in italiano.
+* Prototipazione e test di pipeline NLP italiane.
+* Generazione di risposte sintetiche e dataset per training o valutazione.
+
+---
+
+## Codice per inferenza di esempio
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# 1. Carica modello e tokenizer addestrati
+model_path = "Mattimax/DACMini-IT"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+model.eval()
+
+# 2. Funzione di generazione
+def chat_inference(prompt, max_new_tokens=150, temperature=0.7, top_p=0.9):
+    # Costruisci input nel formato usato in training
+    formatted_prompt = f"<|user|> {prompt.strip()} <|assistant|>"
+
+    # Tokenizza
+    inputs = tokenizer(formatted_prompt, return_tensors="pt")
+
+    # Genera risposta
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=True,
+            pad_token_id=tokenizer.pad_token_id or tokenizer.eos_token_id
+        )
+
+    # Decodifica e rimuovi prompt iniziale
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = generated_text.split("<|assistant|>")[-1].strip()
+    return response
+
+# 3. Esempio d’uso
+if __name__ == "__main__":
+    while True:
+        user_input = input("👤 Utente: ")
+        if user_input.lower() in ["exit", "quit"]:
+            break
+        response = chat_inference(user_input)
+        print(f"🤖 Assistant: {response}\n")
+````
+
+## Referenze
+
+* Dataset: [Mattimax/DATA-AI_Conversation_ITA](https://huggingface.co/datasets/Mattimax/DATA-AI_Conversation_ITA)
+* Modello di base: [DACMini](https://huggingface.co/Mattimax/DACMini)
+* Organizzazione: [M.INC](https://huggingface.co/MINC01)
+* Collezione: [Little_DAC Collection](https://huggingface.co/collections/Mattimax/little-dac-collection-68e11d19a5949d08e672b312)
+
+## Citazione
+
+Se utilizzi **Mattimax/DACMini-IT** in un progetto, un articolo o qualsiasi lavoro, ti chiediamo gentilmente di citarlo usando il file `CITATION.bib` incluso nel repository:
+
+```bibtex
+@misc{mattimax2025dacminiit,
+    title = {{Mattimax/DACMini-IT}: Un modello di linguaggio open source},
+    author = {Mattimax},
+    howpublished = {\url{https://huggingface.co/Mattimax/DACMini-IT}},
+    year = {2025},
+    note = {License: MIT. Se usi questo modello, per favore citane la fonte originale.}
+}
+```
+---
+
+# English version
+
+## Description
+
+**DACMini-IT** is a compact, instruction-tuned language model for **Italian chat and dialogue**.
+Based on the **GPT-2 Small (Italian adaptation)** architecture, it is designed to be fast, lightweight, and easily deployable on low-resource devices.
+
+Compared to the “base” DACMini, **DACMini-IT** is trained on Italian conversational datasets structured in *user-assistant* format, optimizing its ability to follow instructions and handle natural multi-turn conversations.
+
+---
+
+## Size and technical specs
+
+* **Parameters:** 109M
+* **Architecture:** GPT-2 Small (Italian adaptation)
+* **Max context length:** 512 tokens
+* **Number of layers:** 12
+* **Number of attention heads:** 12
+* **Embedding size:** 768
+* **Vocabulary:** ~50,000 tokens
+* **Quantization:** supported (optional 8-bit / 4-bit via `bitsandbytes`)
+
+---
+
+## Training dataset
+
+Trained on [**Mattimax/DATA-AI_Conversation_ITA**](https://huggingface.co/datasets/Mattimax/DATA-AI_Conversation_ITA), an Italian instruction-tuned conversational dataset containing structured *prompt-response* pairs designed to promote coherent, natural, and grammatically correct answers.
+
+---
+
+## Objectives
+
+* Italian-language chatbot with instruction-following capabilities.
+* Concise, clear, and natural responses in multi-turn contexts.
+* Lightweight or offline applications where model size is a constraint.
+
+---
+
+## Warnings and limitations
+
+* **Experimental** model: may produce logical errors or irrelevant answers.
+* Not trained on sensitive topics or specialized content.
+* Limited performance on very long conversations or complex prompts.
+* Not intended for commercial use without further validation.
+
+---
+
+## Recommended use
+
+* Lightweight or offline Italian chatbot applications.
+* Prototyping and testing of Italian NLP pipelines.
+* Synthetic response generation and datasets for training or evaluation.
+
+---
+
+## Example inference code
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# 1. Load trained model and tokenizer
+model_path = "Mattimax/DACMini-IT"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(model_path)
+model.eval()
+
+# 2. Generation function
+def chat_inference(prompt, max_new_tokens=150, temperature=0.7, top_p=0.9):
+    # Build input in the format used during training
+    formatted_prompt = f"<|user|> {prompt.strip()} <|assistant|>"
+
+    # Tokenize
+    inputs = tokenizer(formatted_prompt, return_tensors="pt")
+
+    # Generate response
+    with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=True,
+            pad_token_id=tokenizer.pad_token_id or tokenizer.eos_token_id
+        )
+
+    # Decode and remove initial prompt
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = generated_text.split("<|assistant|>")[-1].strip()
+    return response
+
+# 3. Usage example
+if __name__ == "__main__":
+    while True:
+        user_input = input("👤 User: ")
+        if user_input.lower() in ["exit", "quit"]:
+            break
+        response = chat_inference(user_input)
+        print(f"🤖 Assistant: {response}\n")
+```
+
+---
+
+## References
+
+* Dataset: [Mattimax/DATA-AI_Conversation_ITA](https://huggingface.co/datasets/Mattimax/DATA-AI_Conversation_ITA)
+* Base model: [DACMini](https://huggingface.co/Mattimax/DACMini)
+* Organization: [M.INC](https://huggingface.co/MINC01)
+* Collection: [Little_DAC Collection](https://huggingface.co/collections/Mattimax/little-dac-collection-68e11d19a5949d08e672b312)
+
+---
+
+## Citation
+
+If you use **Mattimax/DACMini-IT** in a project, paper, or any work, please cite it using the `CITATION.bib` file included in the repository:
+
+```bibtex
+@misc{mattimax2025dacminiit,
+    title = {{Mattimax/DACMini-IT}: An open-source language model},
+    author = {Mattimax},
+    howpublished = {\url{https://huggingface.co/Mattimax/DACMini-IT}},
+    year = {2025},
+    note = {License: MIT. If you use this model, please cite the original source.}
+}
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|pad|>": 30001,
+  "<|system|>": 30000
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 30000,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 30001,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 100,
+      "no_repeat_ngram_size": 4,
+      "num_beams": 10,
+      "repetition_penalty": 10.0,
+      "temperature": 2.0,
+      "top_k": 20,
+      "top_p": 0.9
+    }
+  },
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 30002
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30000,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 30001,
+  "transformers_version": "4.57.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6e493356331bd4aac20e182e51329ba02e6af54f6ff1f52c28dc04bdb350a9
+size 435550848

onnx_model_directory/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|pad|>": 30001,
+  "<|system|>": 30000
+}

onnx_model_directory/config.json

@@ -0,0 +1,47 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 30000,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 30001,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 100,
+      "no_repeat_ngram_size": 4,
+      "num_beams": 10,
+      "repetition_penalty": 10.0,
+      "temperature": 2.0,
+      "top_k": 20,
+      "top_p": 0.9
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_cache": false,
+  "vocab_size": 30002
+}

onnx_model_directory/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30000,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 30001,
+  "transformers_version": "4.55.4"
+}

onnx_model_directory/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c852ac40afc81214236a147b1f2573fd075bafd064a79ef403a518ec4655e7b6
+size 435940686

onnx_model_directory/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|system|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

onnx_model_directory/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|system|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|system|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|system|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] != 'system' %}<|system|>\nTi chiami DACMini, un modello di intelligenza artificiale creato da M.INC.{% endif %}\n{% for message in messages %}{% if message['role'] == 'user' %}<|user|>\n{{ message['content'] }}{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{% endif %}{% endfor %}\n<|assistant|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d542748374d9b107613de2edff26ae1c5410d5b87edbf57cee57f3cb90272c0f
+size 5777