Upload DuchifatCore

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "DuchifatCore"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_duchifat_v2.DuchifatConfig",
+    "AutoModelForCausalLM": "modeling_duchifat_v2.DuchifatCore"
+  },
+  "dtype": "bfloat16",
+  "hidden_size": 768,
+  "max_seq": 1024,
+  "model_type": "duchifat_v2",
+  "nhead": 12,
+  "num_layers": 12,
+  "transformers_version": "5.0.0",
+  "vocab_size": 33152
+}

configuration_duchifat_v2.py

@@ -0,0 +1,20 @@
+from transformers import PretrainedConfig
+
+class DuchifatConfig(PretrainedConfig):
+    model_type = "duchifat_v2"
+
+    def __init__(
+        self,
+        vocab_size=50257,
+        hidden_size=768,
+        num_layers=12,
+        nhead=12,
+        max_seq=1024,
+        **kwargs
+    ):
+        super().__init__(**kwargs)
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_layers = num_layers
+        self.nhead = nhead
+        self.max_seq = max_seq

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80c08d30ae98079619ca192052005d6f87070f3c956d2f9e1bf041ccd5a0d33
+size 273541208

modeling_duchifat_v2.py

@@ -0,0 +1,99 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import PreTrainedModel
+from transformers.modeling_outputs import CausalLMOutput
+from .configuration_duchifat_v2 import DuchifatConfig
+
+class DuchifatBlock(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.ln1 = nn.LayerNorm(config.hidden_size)
+        self.qkv = nn.Linear(config.hidden_size, 3 * config.hidden_size)
+        self.wo = nn.Linear(config.hidden_size, config.hidden_size)
+        self.ln2 = nn.LayerNorm(config.hidden_size)
+        self.mlp = nn.Sequential(
+            nn.Linear(config.hidden_size, 4 * config.hidden_size),
+            nn.GELU(approximate='tanh'),
+            nn.Linear(4 * config.hidden_size, config.hidden_size)
+        )
+        self.n_head = config.nhead
+        self.head_dim = config.hidden_size // config.nhead
+
+    def forward(self, x):
+        norm_x = self.ln1(x)
+        B, T, C = norm_x.size()
+        qkv = self.qkv(norm_x).view(B, T, 3, self.n_head, self.head_dim).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]
+
+        # Flash Attention (SDPA)
+        attn_out = F.scaled_dot_product_attention(q, k, v, is_causal=True)
+        attn_out = attn_out.transpose(1, 2).contiguous().view(B, T, C)
+
+        x = x + self.wo(attn_out)
+        x = x + self.mlp(self.ln2(x))
+        return x
+
+class DuchifatPreTrainedModel(PreTrainedModel):
+    config_class = DuchifatConfig
+    base_model_prefix = "model"
+    _no_split_modules = ["DuchifatBlock"]
+
+class DuchifatCore(DuchifatPreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.wte = nn.Embedding(config.vocab_size, config.hidden_size)
+        self.wpe = nn.Embedding(config.max_seq, config.hidden_size)
+        self.blocks = nn.ModuleList([DuchifatBlock(config) for _ in range(config.num_layers)])
+        self.ln_f = nn.LayerNorm(config.hidden_size)
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        # Initialize weights
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.wte
+
+    def set_input_embeddings(self, value):
+        self.wte = value
+
+    def forward(self, input_ids=None, attention_mask=None, labels=None, **kwargs):
+        # טיפול במקרה שבו input_ids לא נשלח כראוי
+        if input_ids is None:
+            raise ValueError("You must specify input_ids")
+            
+        B, T = input_ids.size()
+        device = input_ids.device
+        
+        # בניית פוזיציות (Absolute Positional Embeddings)
+        pos = torch.arange(0, T, dtype=torch.long, device=device)
+        
+        x = self.wte(input_ids) + self.wpe(pos)
+
+        for block in self.blocks:
+            x = block(x)
+
+        logits = self.lm_head(self.ln_f(x))
+
+        loss = None
+        if labels is not None:
+            # Shift logits/labels עבור Causal Language Modeling (הזזה של 1 ימינה)
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            loss = F.cross_entropy(shift_logits.view(-1, self.config.vocab_size), shift_labels.view(-1))
+
+        return CausalLMOutput(
+            loss=loss,
+            logits=logits
+        )
+
+    # פונקציה חיונית שמאפשרת ל-generate לעבוד
+    def prepare_inputs_for_generation(self, input_ids, attention_mask=None, **kwargs):
+        return {
+            "input_ids": input_ids,
+            "attention_mask": attention_mask
+        }
+
+    # תמיכה ב-Beam Search ובדיקות קאש בסיסיות
+    def _reorder_cache(self, past_key_values, beam_idx):
+        return past_key_values