---
datasets:
- TinyStories
language:
- en
base_model:
- timmyd69/Lama2-7b-chat-hf-oslo-merged-model-Q2_K-GGUF
---
Leap0 Model

### Model Description

This is the Leap0 model, designed for text generation tasks. It leverages the GPT-2 tokenizer and architecture but is specifically trained on the Tiny Stories dataset.

## Model Architecture

- **Model Type**: Custom GPT-2
- **Number of Layers**: 8
- **Number of Heads**: 8
- **Embedding Size**: 768
- **Block Size**: 768
- **Vocabulary Size**: 50257
- **Dropout Rate**: 0.1
- **Attention Mechanism**: Causal Self-Attention
- **Encoding**: GPT-2 Tokenizer

## Training Details

- **Dataset**: Tiny Stories

## How to Use
# change the input as per your desired string 

"""
import torch
import json
from transformers import GPT2Tokenizer
from safetensors.torch import load_file
import os
import math
import time
import inspect
from dataclasses import dataclass
import torch
import torch.nn as nn
from torch.nn import functional as F
from datasets import load_dataset

# Load the dataset
dataset = load_dataset("hellaswag", trust_remote_code=True)
print(dataset)

# Define the CausalSelfAttention class
class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd)
        self.c_proj.NANOGPT_SCALE_INIT = 1
        self.n_head = config.n_head
        self.n_embd = config.n_embd

    def forward(self, x):
        B, T, C = x.size()
        qkv = self.c_attn(x)
        q, k, v = qkv.split(self.n_embd, dim=2)
        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        y = F.scaled_dot_product_attention(q, k, v, is_causal=True)
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.c_proj(y)
        return y

# Define the MLP class
class MLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
        self.gelu = nn.GELU(approximate='tanh')
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
        self.c_proj.NANOGPT_SCALE_INIT = 1

    def forward(self, x):
        x = self.c_fc(x)
        x = self.gelu(x)
        x = self.c_proj(x)
        return x

# Define the Block class
class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.n_embd)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln_1(x))
        x = x + self.mlp(self.ln_2(x))
        return x

# Define the GPTConfig class
@dataclass
class GPTConfig:
    block_size: int = 768
    vocab_size: int = 50257
    n_layer: int = 8
    n_head: int = 8
    n_embd: int = 768
    dropout: float = 0.1
    model_type: str = "custom_gpt"

    def to_dict(self):
        return self.__dict__

    @classmethod
    def from_dict(cls, config_dict):
        return cls(**config_dict)

# Define the GPT class
class GPT(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config

        self.transformer = nn.ModuleDict(dict(
            wte=nn.Embedding(config.vocab_size, config.n_embd),
            wpe=nn.Embedding(config.block_size, config.n_embd),
            h=nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f=nn.LayerNorm(config.n_embd),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)

        # Weight sharing scheme
        self.transformer.wte.weight = self.lm_head.weight

        # Initialize parameters
        self.apply(self._init_weights)

    def _init_weights(self, module):
        if isinstance(module, nn.Linear):
            std = 0.02
            if hasattr(module, 'NANOGPT_SCALE_INIT'):
                std *= (2 * self.config.n_layer) ** -0.5
            torch.nn.init.normal_(module.weight, mean=0.0, std=std)
            if module.bias is not None:
                torch.nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)

    def forward(self, idx, targets=None):
        B, T = idx.size()
        assert T <= self.config.block_size, f"Cannot forward sequence of length {T}, block size is only {self.config.block_size}"
        pos = torch.arange(0, T, dtype=torch.long, device=idx.device)
        pos_emb = self.transformer.wpe(pos)
        tok_emb = self.transformer.wte(idx)
        x = tok_emb + pos_emb
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)
        logits = self.lm_head(x)
        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
        return logits, loss

# Manually specify the paths to the config and model files
config_path = "/home/nll-workstation/Desktop/config.json"
model_path = "/home/nll-workstation/Desktop/model.safetensors"

# Load the configuration from the specified JSON file
with open(config_path, "r") as f:
    config_dict = json.load(f)
config = GPTConfig.from_dict(config_dict)

# Load the model weights from the specified .safetensors file
tensors = load_file(model_path)

# Instantiate the model with the loaded config
model = GPT(config)

# Load the state dict (weights) into the model
model.load_state_dict(tensors, strict=False)

# Set the model to evaluation mode
model.eval()

# Load the tokenizer (same tokenizer used during training)
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")

# Prepare input text and tokenize it
input_text = "once upon a time in the village of "
input_ids = tokenizer.encode(input_text, return_tensors="pt")

# Run inference (forward pass) through the model
logits, _ = model(input_ids)  # Forward pass, extract logits from the tuple

# Get predicted token IDs by taking the argmax of logits
predicted_ids = torch.argmax(logits, dim=-1)

# Convert predicted token IDs to text
output_text = tokenizer.decode(predicted_ids[0], skip_special_tokens=True)

# Print input and output
print("Input Text:", input_text)
print("Output Text:", output_text)
"""