初始化项目，由ModelHub XC社区提供模型

Model: xxrickyxx/Ailo152m-events-it
Source: Original Platform

.gitattributes

@@ -0,0 +1,3 @@
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- it
+tags:
+- text-generation
+- information-extraction
+- structured-output
+- json
+- ner
+- small-language-model
+- edge-ai
+- on-device
+- ollama
+- gguf
+- calendar
+- italian
+pipeline_tag: text-generation
+library_name: gguf
+model-index:
+- name: AILO-152M-Events-IT
+  results: []
+---
+
+# AILO-152M-Events-IT  Linguaggio naturale italiano → evento JSON 🇮🇹⚡
+
+> **Uno specialista da 152M** che trasforma una frase italiana in un **evento JSON** pulito — titolo, data, ora, luogo, partecipanti — e gira quasi ovunque.
+
+Specialista di un solo compito, costruito su AILO-152M: legge la descrizione di un evento in italiano e produce JSON strutturato. Minuscolo, veloce, deterministico — ideale come "parser" di un'app calendario, un assistente o un'automazione.
+
+```bash
+ollama run Alieno/ailo-152m-events-it
+>>> Pranzo con Sara domani alle 13 al nuovo ristorante giapponese
+{"titolo": "pranzo", "data": "domani", "ora": "13:00", "luogo": "ristorante giapponese", "partecipanti": ["Sara"]}
+```
+
+## Schema
+
+```json
+{"titolo": str, "data": str|null, "ora": "HH:MM"|null, "luogo": str|null, "partecipanti": [str]}
+```
+
+- **ora normalizzata** a 24h `HH:MM` — *"alle 3 del pomeriggio"* → `15:00`, *"alle 7 e mezza"* → `07:30`, *"a mezzogiorno"* → `12:00`.
+- **data estratta com'è scritta** (*"domani"*, *"venerdì prossimo"*, *"15 marzo"*) — **non** risolta in data di calendario (il modello non ha un orologio).
+- Campi assenti → `null`; nessun partecipante → `[]`.
+
+## Benchmark (test set held-out, 1500 esempi mai visti)
+
+| Metrica | Valore |
+|---|---|
+| **JSON valido** | **100%** |
+| Oggetto esatto | 85.7% |
+| `titolo` | 97.7% |
+| `data` | **100%** |
+| `ora` (normalizzata) | 99.7% |
+| `luogo` | 87.3% |
+| `partecipanti` | 97.7% |
+
+**Generalizza** su frasi libere reali (ha imparato a *copiare lo span*, non a classificare): *"Chiama la mamma stasera"* → `{"titolo": "chiamare la mamma", ...}`, *"Festa di compleanno sabato da Luca con tutti"* → `{"titolo": "festa di compleanno", "luogo": "da Luca", "partecipanti": ["tutti"]}`.
+
+## Usarlo in un'app
+
+```bash
+curl http://localhost:11434/api/chat -d '{
+  "model": "Alieno/ailo-152m-events-it",
+  "messages": [{"role": "user", "content": "Riunione veloce col team lunedì alle 10 su Zoom"}],
+  "stream": false,
+  "options": {"temperature": 0.0}
+}'
+```
+
+Tag: `:latest` / `:q8_0` (migliore, 156 MB) · `:q4_k_m` (più piccolo, 97 MB) · `:f16` (291 MB).
+Usa **temperature 0** per JSON deterministico; `repeat_penalty` basso (1.05) così la punteggiatura del JSON non viene penalizzata.
+
+## Dettagli
+
+| Proprietà | Valore |
+|---|---|
+| Parametri | 151,9M |
+| Architettura | Transformer decoder-only (LayerNorm · RoPE · SwiGLU), 12L/768/12H, ctx 512 |
+| Base | AILO-152M-v2-ITA → specializzato sull'estrazione eventi |
+| Training | 26k coppie sintetiche (frase → JSON), vocabolario aperto/compositivo (~1500 titoli unici) per imparare a **copiare lo span** |
+| Formati | GGUF (q4_k_m, q8_0, f16) + PyTorch |
+
+## Limiti
+
+- **Le date non vengono risolte** in date assolute — la frase è estratta com'è.
+- Forme orarie/locuzioni rare (*"all'una"*, *"col"* al posto di *"con il"*) possono sfuggire.
+- Un evento per input; solo italiano; contesto 512 token (frasi brevi).
+- Per voci di calendario esatte, risolvi la data relativa a valle con fuso/orologio dell'utente.
+
+## Licenza & contatti
+
+Doppia licenza: **CC BY-NC-SA 4.0** (libera per ricerca/didattica/uso personale) + **commerciale** con accordo separato.
+**Riccardo Sparacino** — [LinkedIn](https://www.linkedin.com/in/riccardo-sparacino-developer-php-javascript-mysql-app-ios-android/)
+
+```bibtex
+@misc{ailo152m_events_it_2026,
+  title  = {AILO-152M-Events-IT: estrattore italiano da linguaggio naturale a evento JSON},
+  author = {Sparacino, Riccardo}, year = {2026},
+  note   = {Dual-licensed CC BY-NC-SA 4.0 / commerciale}
+}
+```

ailo-extract-it-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f756a45bbe2e68a6ae505974b58b48a05456044db0bdeb83c343b7d61191f448
+size 305537728

ailo-extract-it-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9272e8ceeb744c7fe7f5468ba68b4c9f67868e72378a47e2e3c845841e8d63b7
+size 101775456

ailo-extract-it-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8d08de5cc4ade44107012f37d19b33bba7253c914340258e1ec174c5786bb5
+size 163184448

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "AILOForCausalLM"
+  ],
+  "model_type": "ailo",
+  "vocab_size": 50257,
+  "hidden_size": 768,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 12,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.57.0",
+  "auto_map": {
+    "AutoConfig": "configuration_ailo.AILOConfig",
+    "AutoModelForCausalLM": "modeling_ailo.AILOForCausalLM"
+  }
+}

configuration_ailo.py

@@ -0,0 +1,41 @@
+"""
+AILO Configuration for HuggingFace Transformers
+"""
+
+from transformers import PretrainedConfig
+
+
+class AILOConfig(PretrainedConfig):
+    """Configuration class for AILO model."""
+    
+    model_type = "ailo"
+    
+    def __init__(
+        self,
+        vocab_size: int = 50257,
+        hidden_size: int = 768,
+        num_hidden_layers: int = 12,
+        num_attention_heads: int = 12,
+        intermediate_size: int = 3072,
+        max_position_embeddings: int = 512,
+        hidden_dropout_prob: float = 0.1,
+        attention_probs_dropout_prob: float = 0.1,
+        bos_token_id: int = 50256,
+        eos_token_id: int = 50256,
+        pad_token_id: int = 50256,
+        **kwargs
+    ):
+        super().__init__(
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            pad_token_id=pad_token_id,
+            **kwargs
+        )
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.intermediate_size = intermediate_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob

modeling_ailo.py

@@ -0,0 +1,216 @@
+"""
+AILO Model for HuggingFace Transformers - Matching original architecture
+"""
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import math
+from typing import Optional, Tuple, Union
+
+from transformers import PreTrainedModel
+from transformers.generation import GenerationMixin
+from transformers.modeling_outputs import CausalLMOutputWithPast
+
+try:
+    from .configuration_ailo import AILOConfig
+except ImportError:
+    from configuration_ailo import AILOConfig
+
+
+class RotaryPositionalEmbedding(nn.Module):
+    """Rotary Position Embedding (RoPE)."""
+    
+    def __init__(self, dim: int, max_seq_len: int = 512, base: int = 10000):
+        super().__init__()
+        inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / dim))
+        self.register_buffer("inv_freq", inv_freq)
+        self.max_seq_len = max_seq_len
+        
+    def forward(self, x: torch.Tensor, seq_len: int) -> Tuple[torch.Tensor, torch.Tensor]:
+        t = torch.arange(seq_len, device=x.device).type_as(self.inv_freq)
+        freqs = torch.einsum("i,j->ij", t, self.inv_freq)
+        emb = torch.cat((freqs, freqs), dim=-1)
+        return emb.cos(), emb.sin()
+
+
+def apply_rotary_pos_emb(q, k, cos, sin):
+    """Apply rotary position embedding."""
+    def rotate_half(x):
+        x1, x2 = x[..., :x.shape[-1]//2], x[..., x.shape[-1]//2:]
+        return torch.cat((-x2, x1), dim=-1)
+    
+    q_embed = (q * cos) + (rotate_half(q) * sin)
+    k_embed = (k * cos) + (rotate_half(k) * sin)
+    return q_embed, k_embed
+
+
+class AILOAttention(nn.Module):
+    """Multi-head attention matching original structure."""
+    
+    def __init__(self, config: AILOConfig):
+        super().__init__()
+        self.n_heads = config.num_attention_heads
+        self.head_dim = config.hidden_size // config.num_attention_heads
+        self.scale = self.head_dim ** -0.5
+        
+        # Match original: separate q, k, v projections
+        self.q_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
+        self.k_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
+        self.v_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
+        self.out_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
+        
+        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
+        self.rotary = RotaryPositionalEmbedding(self.head_dim, config.max_position_embeddings)
+        
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        B, T, C = x.shape
+        
+        q = self.q_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
+        k = self.k_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
+        v = self.v_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
+        
+        cos, sin = self.rotary(x, T)
+        cos, sin = cos.unsqueeze(0).unsqueeze(0), sin.unsqueeze(0).unsqueeze(0)
+        q, k = apply_rotary_pos_emb(q, k, cos, sin)
+        
+        attn = (q @ k.transpose(-2, -1)) * self.scale
+        
+        # Causal mask
+        causal_mask = torch.triu(torch.ones(T, T, device=x.device), diagonal=1).bool()
+        attn = attn.masked_fill(causal_mask.unsqueeze(0).unsqueeze(0), float('-inf'))
+        
+        attn = F.softmax(attn, dim=-1)
+        attn = self.dropout(attn)
+        
+        out = (attn @ v).transpose(1, 2).reshape(B, T, C)
+        return self.out_proj(out)
+
+
+class AILOMLP(nn.Module):
+    """Feed-forward with SwiGLU - matching original w1, w2, w3 structure."""
+    
+    def __init__(self, config: AILOConfig):
+        super().__init__()
+        # Match original: w1 [3072, 768], w2 [768, 3072], w3 [3072, 768]
+        self.w1 = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
+        self.w2 = nn.Linear(config.intermediate_size, config.hidden_size, bias=False)
+        self.w3 = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+        
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        # SwiGLU: w2(silu(w1(x)) * w3(x))
+        return self.dropout(self.w2(F.silu(self.w1(x)) * self.w3(x)))
+
+
+class AILOBlock(nn.Module):
+    """Transformer block matching original structure."""
+    
+    def __init__(self, config: AILOConfig):
+        super().__init__()
+        self.ln1 = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
+        self.attn = AILOAttention(config)
+        self.ln2 = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
+        self.ff = AILOMLP(config)
+        
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x + self.attn(self.ln1(x))
+        x = x + self.ff(self.ln2(x))
+        return x
+
+
+class AILOPreTrainedModel(PreTrainedModel):
+    """Base class for AILO models."""
+    
+    config_class = AILOConfig
+    base_model_prefix = "ailo"
+    
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            nn.init.normal_(module.weight, mean=0.0, std=0.02)
+        elif isinstance(module, nn.Embedding):
+            nn.init.normal_(module.weight, mean=0.0, std=0.02)
+
+
+class AILOForCausalLM(AILOPreTrainedModel, GenerationMixin):
+    """AILO model for causal language modeling - matching original structure."""
+    
+    def __init__(self, config: AILOConfig):
+        super().__init__(config)
+        
+        # Match original naming: tok_emb, blocks, ln_f, head
+        self.tok_emb = nn.Embedding(config.vocab_size, config.hidden_size)
+        self.blocks = nn.ModuleList([AILOBlock(config) for _ in range(config.num_hidden_layers)])
+        self.ln_f = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
+        self.head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+        
+        # Weight tying
+        self.head.weight = self.tok_emb.weight
+        
+        self.post_init()
+    
+    def forward(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        **kwargs
+    ) -> CausalLMOutputWithPast:
+        x = self.tok_emb(input_ids)
+        
+        for block in self.blocks:
+            x = block(x)
+        
+        x = self.ln_f(x)
+        logits = self.head(x)
+        
+        loss = None
+        if labels is not None:
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            loss = F.cross_entropy(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
+        
+        return CausalLMOutputWithPast(loss=loss, logits=logits)
+    
+    def prepare_inputs_for_generation(self, input_ids, **kwargs):
+        return {"input_ids": input_ids}
+    
+    @torch.no_grad()
+    def generate(
+        self,
+        input_ids: torch.LongTensor,
+        max_new_tokens: int = 100,
+        temperature: float = 0.8,
+        top_k: int = 50,
+        top_p: float = 0.95,
+        **kwargs
+    ) -> torch.LongTensor:
+        """Generate text tokens."""
+        for _ in range(max_new_tokens):
+            idx_cond = input_ids[:, -512:]  # Max context
+            outputs = self(idx_cond)
+            logits = outputs.logits[:, -1, :] / temperature
+            
+            # Top-k
+            if top_k > 0:
+                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                logits[logits < v[:, [-1]]] = float('-inf')
+            
+            # Top-p
+            if top_p < 1.0:
+                sorted_logits, sorted_indices = torch.sort(logits, descending=True)
+                cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)
+                sorted_indices_to_remove = cumulative_probs > top_p
+                sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
+                sorted_indices_to_remove[..., 0] = 0
+                indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
+                logits[indices_to_remove] = float('-inf')
+            
+            probs = F.softmax(logits, dim=-1)
+            next_token = torch.multinomial(probs, num_samples=1)
+            input_ids = torch.cat([input_ids, next_token], dim=1)
+            
+            if next_token.item() == self.config.eos_token_id:
+                break
+        
+        return input_ids

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb094ad5f3b48d517c3aa8bda2033e5b6072dad68224872ea888675f4b27266b
+size 607493595