Upload TextGenerationPipeline

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 +1,18 @@
+{
+  "architectures": [
+    "ZZJRabbit22ForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "zzjrabbit22.ZZJRabbit22Config",
+    "AutoModelForCausalLM": "zzjrabbit22.ZZJRabbit22ForCausalLM"
+  },
+  "eos_token_id": 0,
+  "hidden_size": 1024,
+  "model_type": "zzjrabbit22",
+  "num_attention_heads": 8,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "vocab_size": 30000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26866d5bc502fe16f89183c817b279db87d17246b51ced7fe695cf8378769ac4
+size 682448056

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "zzjrabbit22.ZZJRabbit22Tokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "tokenizer_class": "ZZJRabbit22Tokenizer"
+}

zzjrabbit22.py

@@ -0,0 +1,250 @@
+import math
+import os.path
+from typing import Optional, Union
+
+import torch
+import torch.nn as nn
+from tokenizers import Tokenizer
+from transformers import (
+    GenerationMixin,
+    PretrainedConfig,
+    PreTrainedModel,
+    PreTrainedTokenizer,
+)
+from transformers.modeling_outputs import BaseModelOutput, CausalLMOutput
+
+
+class ZZJRabbit22Config(PretrainedConfig):
+    model_type = "zzjrabbit22"
+
+    def __init__(
+        self,
+        num_layers: int = 12,
+        num_attention_heads: int = 8,
+        vocab_size: int = 10000,
+        hidden_size: int = 1024,
+        **kwargs,
+    ):
+        self.num_layers = num_layers
+        self.num_attention_heads = num_attention_heads
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        assert hidden_size % num_attention_heads == 0
+        super().__init__(**kwargs)
+
+
+class ZZJRabbit22PE(nn.Module):
+    def __init__(self, hidden_size: int, max_len: int = 32768):
+        super().__init__()
+        pe = torch.zeros(max_len, hidden_size)
+        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
+        div_term = torch.exp(
+            torch.arange(0, hidden_size, 2).float() * (-math.log(10000.0) / hidden_size)
+        )
+        pe[:, 0::2] = torch.sin(position * div_term)
+        pe[:, 1::2] = torch.cos(position * div_term)
+        pe = pe.unsqueeze(0).transpose(0, 1)
+        self.register_buffer("pe", pe)
+
+    def forward(self, x: torch.Tensor):
+        return x + self.pe[: x.size(0), :]
+
+
+class ZZJRabbit22Attention(nn.Module):
+    def __init__(self, config: ZZJRabbit22Config):
+        super().__init__()
+        self.config = config
+        self.head_dim = config.hidden_size // config.num_attention_heads
+        self.q_proj = nn.Linear(config.hidden_size, config.hidden_size)
+        self.k_proj = nn.Linear(config.hidden_size, config.hidden_size)
+        self.v_proj = nn.Linear(config.hidden_size, config.hidden_size)
+        self.out_proj = nn.Linear(config.hidden_size, config.hidden_size)
+        self.dropout = nn.Dropout(0.1)
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        key_padding_mask: Optional[torch.BoolTensor] = None,
+        attn_mask: Optional[torch.BoolTensor] = None,
+    ):
+        batch_size = x.size(0)
+        Q = (
+            self.q_proj(x)
+            .view(batch_size, -1, self.config.num_attention_heads, self.head_dim)
+            .transpose(1, 2)
+        )
+        K = (
+            self.k_proj(x)
+            .view(batch_size, -1, self.config.num_attention_heads, self.head_dim)
+            .transpose(1, 2)
+        )
+        V = (
+            self.v_proj(x)
+            .view(batch_size, -1, self.config.num_attention_heads, self.head_dim)
+            .transpose(1, 2)
+        )
+        scores = torch.matmul(Q, K.transpose(-2, -1)) / torch.sqrt(
+            torch.tensor(self.head_dim, dtype=torch.float32)
+        )
+        if key_padding_mask is not None:
+            scores = scores.masked_fill(
+                key_padding_mask.view(batch_size, 1, 1, -1), float("-inf")
+            )
+        if attn_mask is not None:
+            scores = scores.masked_fill(attn_mask, float("-inf"))
+        attn_weights = nn.functional.softmax(scores, dim=-1)
+        attn_weights = self.dropout(attn_weights)
+        context = torch.matmul(attn_weights, V)
+        context = context.transpose(1, 2).contiguous()
+        context = context.view(batch_size, -1, self.config.hidden_size)
+        return self.out_proj(context)
+
+
+class ZZJRabbit22Layer(nn.Module):
+    def __init__(self, config: ZZJRabbit22Config):
+        super().__init__()
+        self.attn = ZZJRabbit22Attention(config)
+        self.l1 = nn.Linear(config.hidden_size, config.hidden_size)
+        self.l2 = nn.Linear(config.hidden_size, config.hidden_size)
+        self.activate = nn.ReLU()
+        self.norm = nn.RMSNorm(config.hidden_size)
+
+    def forward(
+        self, x: torch.Tensor, attention_mask: Optional[torch.Tensor] = None
+    ) -> torch.Tensor:
+        key_padding_mask = None
+        attn_mask = None
+        if self.training:
+            attn_mask = torch.gt(
+                torch.triu(torch.ones(x.size(-2), x.size(-2), device=x.device), 1), 0
+            )
+        if attention_mask is not None:
+            key_padding_mask = torch.lt(attention_mask, 1)
+        attn = self.attn(
+            x,
+            key_padding_mask=key_padding_mask,
+            attn_mask=attn_mask,
+        )[0]
+        x = self.norm(x + attn)
+        o = self.l1(x)
+        o = self.activate(o)
+        o = self.l2(o)
+        return self.norm(x + o)
+
+
+class ZZJRabbit22Model(PreTrainedModel):
+    config_class = ZZJRabbit22Config
+
+    def __init__(self, config: ZZJRabbit22Config, **kwargs):
+        super().__init__(config, **kwargs)
+        self.config = config
+        self.emb = nn.Embedding(config.vocab_size, config.hidden_size)
+        self.pe = ZZJRabbit22PE(config.hidden_size)
+        self.layers = nn.ModuleList(
+            [ZZJRabbit22Layer(config) for _ in range(config.num_layers)]
+        )
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        return_dict: Optional[bool] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        **kwargs,
+    ):
+        res = self.emb(input_ids)
+        res = self.pe(res)
+        res = res
+        for l in self.layers:
+            res = l(res, attention_mask)
+        if not return_dict:
+            return (res,)
+        else:
+            return BaseModelOutput(res)
+
+
+class ZZJRabbit22ForCausalLM(PreTrainedModel, GenerationMixin):
+    config_class = ZZJRabbit22Config
+
+    def __init__(self, config, **kwargs):
+        super().__init__(config, **kwargs)
+        self.model = ZZJRabbit22Model(config, **kwargs)
+        self.l = nn.Linear(config.hidden_size, config.vocab_size)
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        return_dict: Optional[bool] = None,
+        labels: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        logits_to_keep: Union[int, torch.Tensor] = 0,
+        **kwargs,
+    ):
+        # print(input_ids, return_dict, labels, attention_mask, logits_to_keep, kwargs)
+        hidden = self.model(input_ids=input_ids, attention_mask=attention_mask)[0]
+        logits = self.l(
+            hidden[
+                :,
+                slice(-logits_to_keep, None)
+                if isinstance(logits_to_keep, int)
+                else logits_to_keep,
+                :,
+            ]
+        )
+        if labels is not None:
+            loss = self.loss_function(
+                logits=logits,
+                labels=labels,
+                vocab_size=self.config.vocab_size,
+                **kwargs,
+            )
+            print(loss)
+        if not return_dict:
+            return (loss, logits) if labels is not None else (logits,)
+        else:
+            return (
+                CausalLMOutput(logits=logits, loss=loss)
+                if labels is not None
+                else CausalLMOutput(logits=logits)
+            )
+
+    @classmethod
+    def can_generate(cls):
+        return True
+
+    def prepare_inputs_for_generation(self, input_ids, **kwargs):
+        return {"input_ids": input_ids}
+
+
+class ZZJRabbit22Tokenizer(PreTrainedTokenizer):
+    vocab_files_names = {"tokenizers_file": "tokenizer.json"}
+
+    def __init__(self, tokenizers_file, **kwargs):
+        self.internal = Tokenizer.from_file(tokenizers_file)
+        super().__init__(**kwargs)
+
+    def get_vocab(self):
+        return {self.internal.id_to_token(i): i for i in range(self.vocab_size)}
+
+    def tokenize(self, text, **kwargs):
+        return self.internal.encode(text).tokens
+
+    def convert_tokens_to_ids(self, tokens):
+        return (
+            self.internal.token_to_id(tokens)
+            if isinstance(tokens, str)
+            else [self.internal.token_to_id(t) for t in tokens]
+        )
+
+    def decode(self, tokens, skip_special_tokens=True, **kwargs):
+        if isinstance(tokens, torch.Tensor):
+            tokens = tokens.tolist()
+        return self.internal.decode(tokens, skip_special_tokens=skip_special_tokens)
+
+    @property
+    def vocab_size(self):
+        return self.internal.get_vocab_size()
+
+    def save_vocabulary(self, path, *args, **kwargs) -> tuple[str]:
+        p = os.path.join(path, "tokenizer.json")
+        self.internal.save(p)
+        return (p,)