Upload LstmForCausalLM

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 +1,22 @@
+{
+  "_name_or_path": "/home/alex/Workspace/LSTM_LM/lstm_v1/checkpoint-2000",
+  "architectures": [
+    "LstmForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_lstm.LstmConfig",
+    "AutoModelForCausalLM": "modeling_lstm.LstmForCausalLM"
+  },
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_size": 2048,
+  "initializer_gain": 1,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "model_type": "lstm",
+  "num_hidden_layers": 2,
+  "pad_token_id": 128004,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "vocab_size": 128256
+}

configuration_lstm.py

@@ -0,0 +1,34 @@
+from transformers import PretrainedConfig
+
+
+class LstmConfig(PretrainedConfig):
+    model_type = "lstm"
+
+    def __init__(
+        self,
+        num_hidden_layers=16,
+        hidden_size = 640,
+        vocab_size = 128256,
+        intermediate_size = 2560,
+        pad_token_id = 128004,
+        bos_token_id = 128000,
+        eos_token_id = 128001,
+        initializer_range = 0.02,
+        initializer_gain = 1,
+        tie_word_embeddings = True,
+        **kwargs,
+    ):
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.vocab_size = vocab_size
+        self.intermediate_size = intermediate_size
+        self.initializer_range = initializer_range
+        self.initializer_gain = initializer_gain
+        self.tie_word_embeddings = tie_word_embeddings
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "pad_token_id": 128004,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c15d74e7f01cbb8e3181ace87b093db3abcd58edfc8d0348f2b77ea9ae56cb0
+size 860903112

modeling_lstm.py

@@ -0,0 +1,171 @@
+from typing import Optional
+import torch
+from torch import nn
+from transformers import PreTrainedModel, GenerationMixin, AutoConfig, AutoModel, AutoModelForCausalLM
+from transformers.modeling_outputs import BaseModelOutputWithNoAttention, CausalLMOutput
+
+from configuration_lstm import LstmConfig
+
+class MLP(nn.Module):
+    def __init__(self, config: LstmConfig):
+        super().__init__()
+        self.config = config
+        self.hidden_size = config.hidden_size
+        self.intermediate_size = config.intermediate_size
+        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.act_fn = nn.SiLU()
+
+    def forward(self, x):
+        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
+        return down_proj
+
+class LstmLayer(nn.Module):
+
+    def __init__(self, config: LstmConfig):
+        super().__init__()
+        
+        self.lstm = nn.LSTM(config.hidden_size, config.hidden_size, num_layers=1, batch_first=True, bias=False)
+        self.mlp = MLP(config)
+        self.input_ln = nn.RMSNorm((config.hidden_size,), eps=1e-6)
+        self.post_ln = nn.RMSNorm((config.hidden_size,), eps=1e-6)
+        
+    def forward(self, hidden_states):
+        lstm_part = self.input_ln(hidden_states)
+        lstm_part, _ = self.lstm(lstm_part)
+        hidden_states = hidden_states + lstm_part
+        
+        mlp_part = self.post_ln(hidden_states)
+        mlp_part = self.mlp(mlp_part)
+        return hidden_states + mlp_part
+
+class LstmPreTrainedModel(PreTrainedModel):
+    config_class = LstmConfig
+    base_model_prefix = "model"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["LstmLayer"]
+
+    def _init_weights(self, module):
+        std = self.config.initializer_range
+        gain = self.config.initializer_gain
+        if isinstance(module, nn.Linear):
+            #nn.init.normal_(module.weight.data, std=std)
+            nn.init.kaiming_uniform_(module.weight.data)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.Embedding):
+            nn.init.normal_(module.weight.data, std=std)
+            if module.padding_idx is not None:
+                module.weight.data[module.padding_idx].zero_()
+        elif isinstance(module, nn.RMSNorm):
+            module.weight.data.fill_(0.4)
+        elif isinstance(module, nn.LSTM):
+            for name, param in module.named_parameters():
+                if "weight" in name:
+                    nn.init.xavier_uniform_(param, gain=gain)
+                elif "bias" in name:
+                    with torch.no_grad():
+                        param.zero_()
+
+class LstmModel(LstmPreTrainedModel):
+
+    def __init__(self, config: LstmConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList(
+            [LstmLayer(config) for layer_idx in range(config.num_hidden_layers)]
+        )
+        self.norm = nn.RMSNorm((config.hidden_size,), eps=1e-6)
+        self.gradient_checkpointing = False
+        
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        inputs_embeds: Optional[torch.LongTensor] = None,
+        **kwargs,
+    ) -> BaseModelOutputWithNoAttention:
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
+        
+        if inputs_embeds is None:
+            hidden_states = self.embed_tokens(input_ids)
+        
+        for block in self.layers:
+            if self.gradient_checkpointing and self.training:
+                hidden_states = self._gradient_checkpointing_func(
+                    block.__call__,
+                    hidden_states,
+                )
+            else:
+                hidden_states = block(hidden_states)
+        
+        last_hidden_state = self.norm(hidden_states)
+        return BaseModelOutputWithNoAttention(
+            last_hidden_state=last_hidden_state
+        )
+
+class LstmForCausalLM(LstmPreTrainedModel, GenerationMixin):
+    _tied_weights_keys = ["lm_head.weight"]
+
+    def __init__(self, config: LstmConfig):
+        super().__init__(config)
+        self.model = LstmModel(config)
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.model.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.model.embed_tokens = value
+
+    def get_output_embeddings(self):
+        return self.lm_head
+
+    def set_output_embeddings(self, new_embeddings):
+        self.lm_head = new_embeddings
+
+    def set_decoder(self, decoder):
+        self.model = decoder
+
+    def get_decoder(self):
+        return self.model
+    
+    def forward(
+        self,
+        input_ids: torch.LongTensor = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        num_logits_to_keep: int = 0,
+        **kwargs,
+    ):
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
+        
+        hidden_states = self.model(input_ids, inputs_embeds).last_hidden_state
+        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
+        logits = self.lm_head(hidden_states[:, -num_logits_to_keep:, :])
+        
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
+            
+        return CausalLMOutput(
+            loss=loss,
+            logits=logits,
+        )
+
+AutoConfig.register("lstm", LstmConfig)
+AutoModel.register(LstmConfig, LstmModel)
+AutoModelForCausalLM.register(LstmConfig, LstmForCausalLM)
+LstmConfig.register_for_auto_class()
+LstmModel.register_for_auto_class("AutoModel")
+LstmForCausalLM.register_for_auto_class("AutoModelForCausalLM")