Upload 4 files

__init__.py

@@ -0,0 +1,6 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
+
+from .generation import Llama, Dialog
+from .model import ModelArgs, Transformer
+from .tokenizer import Tokenizer

generation.py

@@ -0,0 +1,421 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
+
+import json
+import os
+import sys
+import time
+from pathlib import Path
+from typing import List, Literal, Optional, Tuple, TypedDict
+
+import torch
+import torch.nn.functional as F
+from fairscale.nn.model_parallel.initialize import (
+    get_model_parallel_rank,
+    initialize_model_parallel,
+    model_parallel_is_initialized,
+)
+
+from llama.model import ModelArgs, Transformer
+from llama.tokenizer import Tokenizer
+
+Role = Literal["system", "user", "assistant"]
+
+
+class Message(TypedDict):
+    role: Role
+    content: str
+
+
+class CompletionPrediction(TypedDict, total=False):
+    generation: str
+    tokens: List[str]  # not required
+    logprobs: List[float]  # not required
+
+
+class ChatPrediction(TypedDict, total=False):
+    generation: Message
+    tokens: List[str]  # not required
+    logprobs: List[float]  # not required
+
+
+Dialog = List[Message]
+
+B_INST, E_INST = "[INST]", "[/INST]"
+B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
+
+SPECIAL_TAGS = [B_INST, E_INST, "<<SYS>>", "<</SYS>>"]
+UNSAFE_ERROR = "Error: special tags are not allowed as part of the prompt."
+
+
+class Llama:
+    @staticmethod
+    def build(
+        ckpt_dir: str,
+        tokenizer_path: str,
+        max_seq_len: int,
+        max_batch_size: int,
+        model_parallel_size: Optional[int] = None,
+        seed: int = 1,
+    ) -> "Llama":
+        """
+        Build a Llama instance by initializing and loading a pre-trained model.
+
+        Args:
+            ckpt_dir (str): Path to the directory containing checkpoint files.
+            tokenizer_path (str): Path to the tokenizer file.
+            max_seq_len (int): Maximum sequence length for input text.
+            max_batch_size (int): Maximum batch size for inference.
+            model_parallel_size (Optional[int], optional): Number of model parallel processes.
+                If not provided, it's determined from the environment. Defaults to None.
+
+        Returns:
+            Llama: An instance of the Llama class with the loaded model and tokenizer.
+
+        Raises:
+            AssertionError: If there are no checkpoint files in the specified directory,
+                or if the model parallel size does not match the number of checkpoint files.
+
+        Note:
+            This method initializes the distributed process group, sets the device to CUDA,
+            and loads the pre-trained model and tokenizer.
+
+        """
+        if not torch.distributed.is_initialized():
+            torch.distributed.init_process_group("nccl")
+        if not model_parallel_is_initialized():
+            if model_parallel_size is None:
+                model_parallel_size = int(os.environ.get("WORLD_SIZE", 1))
+            initialize_model_parallel(model_parallel_size)
+
+        local_rank = int(os.environ.get("LOCAL_RANK", 0))
+        torch.cuda.set_device(local_rank)
+
+        # seed must be the same in all processes
+        torch.manual_seed(seed)
+
+        if local_rank > 0:
+            sys.stdout = open(os.devnull, "w")
+
+        start_time = time.time()
+        checkpoints = sorted(Path(ckpt_dir).glob("*.pth"))
+        assert len(checkpoints) > 0, f"no checkpoint files found in {ckpt_dir}"
+        assert model_parallel_size == len(
+            checkpoints
+        ), f"Loading a checkpoint for MP={len(checkpoints)} but world size is {model_parallel_size}"
+        ckpt_path = checkpoints[get_model_parallel_rank()]
+        checkpoint = torch.load(ckpt_path, map_location="cpu")
+        with open(Path(ckpt_dir) / "params.json", "r") as f:
+            params = json.loads(f.read())
+
+        model_args: ModelArgs = ModelArgs(
+            max_seq_len=max_seq_len,
+            max_batch_size=max_batch_size,
+            **params,
+        )
+        tokenizer = Tokenizer(model_path=tokenizer_path)
+        model_args.vocab_size = tokenizer.n_words
+        torch.set_default_tensor_type(torch.cuda.HalfTensor)
+        model = Transformer(model_args)
+        model.load_state_dict(checkpoint, strict=False)
+        print(f"Loaded in {time.time() - start_time:.2f} seconds")
+
+        return Llama(model, tokenizer)
+
+    def __init__(self, model: Transformer, tokenizer: Tokenizer):
+        self.model = model
+        self.tokenizer = tokenizer
+
+    @torch.inference_mode()
+    def generate(
+        self,
+        prompt_tokens: List[List[int]],
+        max_gen_len: int,
+        temperature: float = 0.6,
+        top_p: float = 0.9,
+        logprobs: bool = False,
+        echo: bool = False,
+    ) -> Tuple[List[List[int]], Optional[List[List[float]]]]:
+        """
+        Generate text sequences based on provided prompts using the language generation model.
+
+        Args:
+            prompt_tokens (List[List[int]]): List of tokenized prompts, where each prompt is represented as a list of integers.
+            max_gen_len (int): Maximum length of the generated text sequence.
+            temperature (float, optional): Temperature value for controlling randomness in sampling. Defaults to 0.6.
+            top_p (float, optional): Top-p probability threshold for nucleus sampling. Defaults to 0.9.
+            logprobs (bool, optional): Flag indicating whether to compute token log probabilities. Defaults to False.
+            echo (bool, optional): Flag indicating whether to include prompt tokens in the generated output. Defaults to False.
+
+        Returns:
+            Tuple[List[List[int]], Optional[List[List[float]]]]: A tuple containing generated token sequences and, if logprobs is True, corresponding token log probabilities.
+
+        Note:
+            This method uses the provided prompts as a basis for generating text. It employs nucleus sampling to produce text with controlled randomness.
+            If logprobs is True, token log probabilities are computed for each generated token.
+
+        """
+        params = self.model.params
+        bsz = len(prompt_tokens)
+        assert bsz <= params.max_batch_size, (bsz, params.max_batch_size)
+
+        min_prompt_len = min(len(t) for t in prompt_tokens)
+        max_prompt_len = max(len(t) for t in prompt_tokens)
+        assert max_prompt_len <= params.max_seq_len
+        total_len = min(params.max_seq_len, max_gen_len + max_prompt_len)
+
+        pad_id = self.tokenizer.pad_id
+        tokens = torch.full((bsz, total_len), pad_id, dtype=torch.long, device="cuda")
+        for k, t in enumerate(prompt_tokens):
+            tokens[k, : len(t)] = torch.tensor(t, dtype=torch.long, device="cuda")
+        if logprobs:
+            token_logprobs = torch.zeros_like(tokens, dtype=torch.float)
+
+        prev_pos = 0
+        eos_reached = torch.tensor([False] * bsz, device="cuda")
+        input_text_mask = tokens != pad_id
+        if min_prompt_len == total_len:
+            logits = self.model.forward(tokens, prev_pos)
+            token_logprobs = -F.cross_entropy(
+                input=logits.transpose(1, 2),
+                target=tokens,
+                reduction="none",
+                ignore_index=pad_id,
+            )
+
+        for cur_pos in range(min_prompt_len, total_len):
+            logits = self.model.forward(tokens[:, prev_pos:cur_pos], prev_pos)
+            if temperature > 0:
+                probs = torch.softmax(logits[:, -1] / temperature, dim=-1)
+                next_token = sample_top_p(probs, top_p)
+            else:
+                next_token = torch.argmax(logits[:, -1], dim=-1)
+
+            next_token = next_token.reshape(-1)
+            # only replace token if prompt has already been generated
+            next_token = torch.where(
+                input_text_mask[:, cur_pos], tokens[:, cur_pos], next_token
+            )
+            tokens[:, cur_pos] = next_token
+            if logprobs:
+                token_logprobs[:, prev_pos + 1 : cur_pos + 1] = -F.cross_entropy(
+                    input=logits.transpose(1, 2),
+                    target=tokens[:, prev_pos + 1 : cur_pos + 1],
+                    reduction="none",
+                    ignore_index=pad_id,
+                )
+            eos_reached |= (~input_text_mask[:, cur_pos]) & (
+                next_token == self.tokenizer.eos_id
+            )
+            prev_pos = cur_pos
+            if all(eos_reached):
+                break
+
+        if logprobs:
+            token_logprobs = token_logprobs.tolist()
+        out_tokens, out_logprobs = [], []
+        for i, toks in enumerate(tokens.tolist()):
+            # cut to max gen len
+            start = 0 if echo else len(prompt_tokens[i])
+            toks = toks[start : len(prompt_tokens[i]) + max_gen_len]
+            probs = None
+            if logprobs:
+                probs = token_logprobs[i][start : len(prompt_tokens[i]) + max_gen_len]
+            # cut to eos tok if any
+            if self.tokenizer.eos_id in toks:
+                eos_idx = toks.index(self.tokenizer.eos_id)
+                toks = toks[:eos_idx]
+                probs = probs[:eos_idx] if logprobs else None
+            out_tokens.append(toks)
+            out_logprobs.append(probs)
+        return (out_tokens, out_logprobs if logprobs else None)
+
+    def text_completion(
+        self,
+        prompts: List[str],
+        temperature: float = 0.6,
+        top_p: float = 0.9,
+        max_gen_len: Optional[int] = None,
+        logprobs: bool = False,
+        echo: bool = False,
+    ) -> List[CompletionPrediction]:
+        """
+        Perform text completion for a list of prompts using the language generation model.
+
+        Args:
+            prompts (List[str]): List of text prompts for completion.
+            temperature (float, optional): Temperature value for controlling randomness in sampling. Defaults to 0.6.
+            top_p (float, optional): Top-p probability threshold for nucleus sampling. Defaults to 0.9.
+            max_gen_len (Optional[int], optional): Maximum length of the generated completion sequence.
+                If not provided, it's set to the model's maximum sequence length minus 1.
+            logprobs (bool, optional): Flag indicating whether to compute token log probabilities. Defaults to False.
+            echo (bool, optional): Flag indicating whether to include prompt tokens in the generated output. Defaults to False.
+
+        Returns:
+            List[CompletionPrediction]: List of completion predictions, each containing the generated text completion.
+
+        Note:
+            This method generates text completions for the provided prompts, employing nucleus sampling to introduce controlled randomness.
+            If logprobs is True, token log probabilities are computed for each generated token.
+
+        """
+        if max_gen_len is None:
+            max_gen_len = self.model.params.max_seq_len - 1
+        prompt_tokens = [self.tokenizer.encode(x, bos=True, eos=False) for x in prompts]
+        generation_tokens, generation_logprobs = self.generate(
+            prompt_tokens=prompt_tokens,
+            max_gen_len=max_gen_len,
+            temperature=temperature,
+            top_p=top_p,
+            logprobs=logprobs,
+            echo=echo,
+        )
+        if logprobs:
+            return [
+                {
+                    "generation": self.tokenizer.decode(t),
+                    "tokens": [self.tokenizer.decode(x) for x in t],
+                    "logprobs": logprobs_i,
+                }
+                for t, logprobs_i in zip(generation_tokens, generation_logprobs)
+            ]
+        return [{"generation": self.tokenizer.decode(t)} for t in generation_tokens]
+
+    def chat_completion(
+        self,
+        dialogs: List[Dialog],
+        temperature: float = 0.6,
+        top_p: float = 0.9,
+        max_gen_len: Optional[int] = None,
+        logprobs: bool = False,
+    ) -> List[ChatPrediction]:
+        """
+        Generate assistant responses for a list of conversational dialogs using the language generation model.
+
+        Args:
+            dialogs (List[Dialog]): List of conversational dialogs, where each dialog is a list of messages.
+            temperature (float, optional): Temperature value for controlling randomness in sampling. Defaults to 0.6.
+            top_p (float, optional): Top-p probability threshold for nucleus sampling. Defaults to 0.9.
+            max_gen_len (Optional[int], optional): Maximum length of the generated response sequence.
+                If not provided, it's set to the model's maximum sequence length minus 1.
+            logprobs (bool, optional): Flag indicating whether to compute token log probabilities. Defaults to False.
+
+        Returns:
+            List[ChatPrediction]: List of chat predictions, each containing the assistant's generated response.
+
+        Raises:
+            AssertionError: If the last message in a dialog is not from the user.
+            AssertionError: If the dialog roles are not in the required 'user', 'assistant', and optional 'system' order.
+
+        Note:
+            This method generates assistant responses for the provided conversational dialogs.
+            It employs nucleus sampling to introduce controlled randomness in text generation.
+            If logprobs is True, token log probabilities are computed for each generated token.
+
+        """
+        if max_gen_len is None:
+            max_gen_len = self.model.params.max_seq_len - 1
+        prompt_tokens = []
+        unsafe_requests = []
+        for dialog in dialogs:
+            unsafe_requests.append(
+                any([tag in msg["content"] for tag in SPECIAL_TAGS for msg in dialog])
+            )
+            if dialog[0]["role"] == "system":
+                dialog = [
+                    {
+                        "role": dialog[1]["role"],
+                        "content": B_SYS
+                        + dialog[0]["content"]
+                        + E_SYS
+                        + dialog[1]["content"],
+                    }
+                ] + dialog[2:]
+            assert all([msg["role"] == "user" for msg in dialog[::2]]) and all(
+                [msg["role"] == "assistant" for msg in dialog[1::2]]
+            ), (
+                "model only supports 'system', 'user' and 'assistant' roles, "
+                "starting with 'system', then 'user' and alternating (u/a/u/a/u...)"
+            )
+            dialog_tokens: List[int] = sum(
+                [
+                    self.tokenizer.encode(
+                        f"{B_INST} {(prompt['content']).strip()} {E_INST} {(answer['content']).strip()} ",
+                        bos=True,
+                        eos=True,
+                    )
+                    for prompt, answer in zip(
+                        dialog[::2],
+                        dialog[1::2],
+                    )
+                ],
+                [],
+            )
+            assert (
+                dialog[-1]["role"] == "user"
+            ), f"Last message must be from user, got {dialog[-1]['role']}"
+            dialog_tokens += self.tokenizer.encode(
+                f"{B_INST} {(dialog[-1]['content']).strip()} {E_INST}",
+                bos=True,
+                eos=False,
+            )
+            prompt_tokens.append(dialog_tokens)
+
+        generation_tokens, generation_logprobs = self.generate(
+            prompt_tokens=prompt_tokens,
+            max_gen_len=max_gen_len,
+            temperature=temperature,
+            top_p=top_p,
+            logprobs=logprobs,
+        )
+        if logprobs:
+            return [
+                {
+                    "generation": {
+                        "role": "assistant",
+                        "content": self.tokenizer.decode(t)
+                        if not unsafe
+                        else UNSAFE_ERROR,
+                    },
+                    "tokens": [self.tokenizer.decode(x) for x in t],
+                    "logprobs": logprobs_i,
+                }
+                for t, logprobs_i, unsafe in zip(
+                    generation_tokens, generation_logprobs, unsafe_requests
+                )
+            ]
+        return [
+            {
+                "generation": {
+                    "role": "assistant",
+                    "content": self.tokenizer.decode(t) if not unsafe else UNSAFE_ERROR,
+                }
+            }
+            for t, unsafe in zip(generation_tokens, unsafe_requests)
+        ]
+
+
+def sample_top_p(probs, p):
+    """
+    Perform top-p (nucleus) sampling on a probability distribution.
+
+    Args:
+        probs (torch.Tensor): Probability distribution tensor.
+        p (float): Probability threshold for top-p sampling.
+
+    Returns:
+        torch.Tensor: Sampled token indices.
+
+    Note:
+        Top-p sampling selects the smallest set of tokens whose cumulative probability mass
+        exceeds the threshold p. The distribution is renormalized based on the selected tokens.
+
+    """
+    probs_sort, probs_idx = torch.sort(probs, dim=-1, descending=True)
+    probs_sum = torch.cumsum(probs_sort, dim=-1)
+    mask = probs_sum - probs_sort > p
+    probs_sort[mask] = 0.0
+    probs_sort.div_(probs_sort.sum(dim=-1, keepdim=True))
+    next_token = torch.multinomial(probs_sort, num_samples=1)
+    next_token = torch.gather(probs_idx, -1, next_token)
+    return next_token

model.py

@@ -0,0 +1,495 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
+
+import math
+from dataclasses import dataclass
+from typing import Optional, Tuple
+
+import fairscale.nn.model_parallel.initialize as fs_init
+import torch
+import torch.nn.functional as F
+from fairscale.nn.model_parallel.layers import (
+    ColumnParallelLinear,
+    ParallelEmbedding,
+    RowParallelLinear,
+)
+from torch import nn
+
+
+@dataclass
+class ModelArgs:
+    dim: int = 4096
+    n_layers: int = 32
+    n_heads: int = 32
+    n_kv_heads: Optional[int] = None
+    vocab_size: int = -1  # defined later by tokenizer
+    multiple_of: int = 256  # make SwiGLU hidden layer size multiple of large power of 2
+    ffn_dim_multiplier: Optional[float] = None
+    norm_eps: float = 1e-5
+
+    max_batch_size: int = 32
+    max_seq_len: int = 2048
+
+
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float = 1e-6):
+        """
+        Initialize the RMSNorm normalization layer.
+
+        Args:
+            dim (int): The dimension of the input tensor.
+            eps (float, optional): A small value added to the denominator for numerical stability. Default is 1e-6.
+
+        Attributes:
+            eps (float): A small value added to the denominator for numerical stability.
+            weight (nn.Parameter): Learnable scaling parameter.
+
+        """
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def _norm(self, x):
+        """
+        Apply the RMSNorm normalization to the input tensor.
+
+        Args:
+            x (torch.Tensor): The input tensor.
+
+        Returns:
+            torch.Tensor: The normalized tensor.
+
+        """
+        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
+
+    def forward(self, x):
+        """
+        Forward pass through the RMSNorm layer.
+
+        Args:
+            x (torch.Tensor): The input tensor.
+
+        Returns:
+            torch.Tensor: The output tensor after applying RMSNorm.
+
+        """
+        output = self._norm(x.float()).type_as(x)
+        return output * self.weight
+
+
+def precompute_freqs_cis(dim: int, end: int, theta: float = 10000.0):
+    """
+    Precompute the frequency tensor for complex exponentials (cis) with given dimensions.
+
+    This function calculates a frequency tensor with complex exponentials using the given dimension 'dim'
+    and the end index 'end'. The 'theta' parameter scales the frequencies.
+    The returned tensor contains complex values in complex64 data type.
+
+    Args:
+        dim (int): Dimension of the frequency tensor.
+        end (int): End index for precomputing frequencies.
+        theta (float, optional): Scaling factor for frequency computation. Defaults to 10000.0.
+
+    Returns:
+        torch.Tensor: Precomputed frequency tensor with complex exponentials.
+
+    
+        
+
+    """
+    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim))
+    t = torch.arange(end, device=freqs.device)  # type: ignore
+    freqs = torch.outer(t, freqs).float()  # type: ignore
+    freqs_cis = torch.polar(torch.ones_like(freqs), freqs)  # complex64
+    return freqs_cis
+
+
+def reshape_for_broadcast(freqs_cis: torch.Tensor, x: torch.Tensor):
+    """
+    Reshape frequency tensor for broadcasting it with another tensor.
+
+    This function reshapes the frequency tensor to have the same shape as the target tensor 'x'
+    for the purpose of broadcasting the frequency tensor during element-wise operations.
+
+    Args:
+        freqs_cis (torch.Tensor): Frequency tensor to be reshaped.
+        x (torch.Tensor): Target tensor for broadcasting compatibility.
+
+    Returns:
+        torch.Tensor: Reshaped frequency tensor.
+
+    Raises:
+        AssertionError: If the frequency tensor doesn't match the expected shape.
+        AssertionError: If the target tensor 'x' doesn't have the expected number of dimensions.
+    """
+    ndim = x.ndim
+    assert 0 <= 1 < ndim
+    assert freqs_cis.shape == (x.shape[1], x.shape[-1])
+    shape = [d if i == 1 or i == ndim - 1 else 1 for i, d in enumerate(x.shape)]
+    return freqs_cis.view(*shape)
+
+
+def apply_rotary_emb(
+    xq: torch.Tensor,
+    xk: torch.Tensor,
+    freqs_cis: torch.Tensor,
+) -> Tuple[torch.Tensor, torch.Tensor]:
+    """
+    Apply rotary embeddings to input tensors using the given frequency tensor.
+
+    This function applies rotary embeddings to the given query 'xq' and key 'xk' tensors using the provided
+    frequency tensor 'freqs_cis'. The input tensors are reshaped as complex numbers, and the frequency tensor
+    is reshaped for broadcasting compatibility. The resulting tensors contain rotary embeddings and are
+    returned as real tensors.
+
+    Args:
+        xq (torch.Tensor): Query tensor to apply rotary embeddings.
+        xk (torch.Tensor): Key tensor to apply rotary embeddings.
+        freqs_cis (torch.Tensor): Precomputed frequency tensor for complex exponentials.
+
+    Returns:
+        Tuple[torch.Tensor, torch.Tensor]: Tuple of modified query tensor and key tensor with rotary embeddings.
+
+        
+
+    """
+    xq_ = torch.view_as_complex(xq.float().reshape(*xq.shape[:-1], -1, 2))
+    xk_ = torch.view_as_complex(xk.float().reshape(*xk.shape[:-1], -1, 2))
+    freqs_cis = reshape_for_broadcast(freqs_cis, xq_)
+    xq_out = torch.view_as_real(xq_ * freqs_cis).flatten(3)
+    xk_out = torch.view_as_real(xk_ * freqs_cis).flatten(3)
+    return xq_out.type_as(xq), xk_out.type_as(xk)
+
+
+def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """torch.repeat_interleave(x, dim=2, repeats=n_rep)"""
+    bs, slen, n_kv_heads, head_dim = x.shape
+    if n_rep == 1:
+        return x
+    return (
+        x[:, :, :, None, :]
+        .expand(bs, slen, n_kv_heads, n_rep, head_dim)
+        .reshape(bs, slen, n_kv_heads * n_rep, head_dim)
+    )
+
+
+class Attention(nn.Module):
+    """Multi-head attention module."""
+    def __init__(self, args: ModelArgs):
+        """
+        Initialize the Attention module.
+
+        Args:
+            args (ModelArgs): Model configuration parameters.
+
+        Attributes:
+            n_kv_heads (int): Number of key and value heads.
+            n_local_heads (int): Number of local query heads.
+            n_local_kv_heads (int): Number of local key and value heads.
+            n_rep (int): Number of repetitions for local heads.
+            head_dim (int): Dimension size of each attention head.
+            wq (ColumnParallelLinear): Linear transformation for queries.
+            wk (ColumnParallelLinear): Linear transformation for keys.
+            wv (ColumnParallelLinear): Linear transformation for values.
+            wo (RowParallelLinear): Linear transformation for output.
+            cache_k (torch.Tensor): Cached keys for attention.
+            cache_v (torch.Tensor): Cached values for attention.
+
+        """
+        super().__init__()
+        self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads
+        model_parallel_size = fs_init.get_model_parallel_world_size()
+        self.n_local_heads = args.n_heads // model_parallel_size
+        self.n_local_kv_heads = self.n_kv_heads // model_parallel_size
+        self.n_rep = self.n_local_heads // self.n_local_kv_heads
+        self.head_dim = args.dim // args.n_heads
+
+        self.wq = ColumnParallelLinear(
+            args.dim,
+            args.n_heads * self.head_dim,
+            bias=False,
+            gather_output=False,
+            init_method=lambda x: x,
+        )
+        self.wk = ColumnParallelLinear(
+            args.dim,
+            self.n_kv_heads * self.head_dim,
+            bias=False,
+            gather_output=False,
+            init_method=lambda x: x,
+        )
+        self.wv = ColumnParallelLinear(
+            args.dim,
+            self.n_kv_heads * self.head_dim,
+            bias=False,
+            gather_output=False,
+            init_method=lambda x: x,
+        )
+        self.wo = RowParallelLinear(
+            args.n_heads * self.head_dim,
+            args.dim,
+            bias=False,
+            input_is_parallel=True,
+            init_method=lambda x: x,
+        )
+
+        self.cache_k = torch.zeros(
+            (
+                args.max_batch_size,
+                args.max_seq_len,
+                self.n_local_kv_heads,
+                self.head_dim,
+            )
+        ).cuda()
+        self.cache_v = torch.zeros(
+            (
+                args.max_batch_size,
+                args.max_seq_len,
+                self.n_local_kv_heads,
+                self.head_dim,
+            )
+        ).cuda()
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        start_pos: int,
+        freqs_cis: torch.Tensor,
+        mask: Optional[torch.Tensor],
+    ):
+        """
+        Forward pass of the attention module.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+            start_pos (int): Starting position for caching.
+            freqs_cis (torch.Tensor): Precomputed frequency tensor.
+            mask (torch.Tensor, optional): Attention mask tensor.
+
+        Returns:
+            torch.Tensor: Output tensor after attention.
+
+        """
+        bsz, seqlen, _ = x.shape
+        xq, xk, xv = self.wq(x), self.wk(x), self.wv(x)
+
+        xq = xq.view(bsz, seqlen, self.n_local_heads, self.head_dim)
+        xk = xk.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
+        xv = xv.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
+
+        xq, xk = apply_rotary_emb(xq, xk, freqs_cis=freqs_cis)
+
+        self.cache_k = self.cache_k.to(xq)
+        self.cache_v = self.cache_v.to(xq)
+
+        self.cache_k[:bsz, start_pos : start_pos + seqlen] = xk
+        self.cache_v[:bsz, start_pos : start_pos + seqlen] = xv
+
+        keys = self.cache_k[:bsz, : start_pos + seqlen]
+        values = self.cache_v[:bsz, : start_pos + seqlen]
+
+        # repeat k/v heads if n_kv_heads < n_heads
+        keys = repeat_kv(keys, self.n_rep)  # (bs, cache_len + seqlen, n_local_heads, head_dim)
+        values = repeat_kv(values, self.n_rep)  # (bs, cache_len + seqlen, n_local_heads, head_dim)
+
+        xq = xq.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
+        keys = keys.transpose(1, 2) # (bs, n_local_heads, cache_len + seqlen, head_dim)
+        values = values.transpose(1, 2) # (bs, n_local_heads, cache_len + seqlen, head_dim)
+        scores = torch.matmul(xq, keys.transpose(2, 3)) / math.sqrt(self.head_dim)
+        if mask is not None:
+            scores = scores + mask  # (bs, n_local_heads, seqlen, cache_len + seqlen)
+        scores = F.softmax(scores.float(), dim=-1).type_as(xq)
+        output = torch.matmul(scores, values)  # (bs, n_local_heads, seqlen, head_dim)
+        output = output.transpose(1, 2).contiguous().view(bsz, seqlen, -1)
+        return self.wo(output)
+
+
+class FeedForward(nn.Module):
+    def __init__(
+        self,
+        dim: int,
+        hidden_dim: int,
+        multiple_of: int,
+        ffn_dim_multiplier: Optional[float],
+    ):
+        """
+        Initialize the FeedForward module.
+
+        Args:
+            dim (int): Input dimension.
+            hidden_dim (int): Hidden dimension of the feedforward layer.
+            multiple_of (int): Value to ensure hidden dimension is a multiple of this value.
+            ffn_dim_multiplier (float, optional): Custom multiplier for hidden dimension. Defaults to None.
+
+        Attributes:
+            w1 (ColumnParallelLinear): Linear transformation for the first layer.
+            w2 (RowParallelLinear): Linear transformation for the second layer.
+            w3 (ColumnParallelLinear): Linear transformation for the third layer.
+
+        """
+        super().__init__()
+        hidden_dim = int(2 * hidden_dim / 3)
+        # custom dim factor multiplier
+        if ffn_dim_multiplier is not None:
+            hidden_dim = int(ffn_dim_multiplier * hidden_dim)
+        hidden_dim = multiple_of * ((hidden_dim + multiple_of - 1) // multiple_of)
+
+        self.w1 = ColumnParallelLinear(
+            dim, hidden_dim, bias=False, gather_output=False, init_method=lambda x: x
+        )
+        self.w2 = RowParallelLinear(
+            hidden_dim, dim, bias=False, input_is_parallel=True, init_method=lambda x: x
+        )
+        self.w3 = ColumnParallelLinear(
+            dim, hidden_dim, bias=False, gather_output=False, init_method=lambda x: x
+        )
+
+    def forward(self, x):
+        return self.w2(F.silu(self.w1(x)) * self.w3(x))
+
+
+class TransformerBlock(nn.Module):
+    def __init__(self, layer_id: int, args: ModelArgs):
+        """
+        Initialize a TransformerBlock.
+
+        Args:
+            layer_id (int): Identifier for the layer.
+            args (ModelArgs): Model configuration parameters.
+
+        Attributes:
+            n_heads (int): Number of attention heads.
+            dim (int): Dimension size of the model.
+            head_dim (int): Dimension size of each attention head.
+            attention (Attention): Attention module.
+            feed_forward (FeedForward): FeedForward module.
+            layer_id (int): Identifier for the layer.
+            attention_norm (RMSNorm): Layer normalization for attention output.
+            ffn_norm (RMSNorm): Layer normalization for feedforward output.
+
+        """
+        super().__init__()
+        self.n_heads = args.n_heads
+        self.dim = args.dim
+        self.head_dim = args.dim // args.n_heads
+        self.attention = Attention(args)
+        self.feed_forward = FeedForward(
+            dim=args.dim,
+            hidden_dim=4 * args.dim,
+            multiple_of=args.multiple_of,
+            ffn_dim_multiplier=args.ffn_dim_multiplier,
+        )
+        self.layer_id = layer_id
+        self.attention_norm = RMSNorm(args.dim, eps=args.norm_eps)
+        self.ffn_norm = RMSNorm(args.dim, eps=args.norm_eps)
+
+    def forward(
+        self,
+        x: torch.Tensor,
+        start_pos: int,
+        freqs_cis: torch.Tensor,
+        mask: Optional[torch.Tensor],
+    ):
+        """
+        Perform a forward pass through the TransformerBlock.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+            start_pos (int): Starting position for attention caching.
+            freqs_cis (torch.Tensor): Precomputed cosine and sine frequencies.
+            mask (torch.Tensor, optional): Masking tensor for attention. Defaults to None.
+
+        Returns:
+            torch.Tensor: Output tensor after applying attention and feedforward layers.
+
+        """
+        h = x + self.attention(
+            self.attention_norm(x), start_pos, freqs_cis, mask
+        )
+        out = h + self.feed_forward(self.ffn_norm(h))
+        return out
+
+
+class Transformer(nn.Module):
+    def __init__(self, params: ModelArgs):
+        """
+        Initialize a Transformer model.
+
+        Args:
+            params (ModelArgs): Model configuration parameters.
+
+        Attributes:
+            params (ModelArgs): Model configuration parameters.
+            vocab_size (int): Vocabulary size.
+            n_layers (int): Number of layers in the model.
+            tok_embeddings (ParallelEmbedding): Token embeddings.
+            layers (torch.nn.ModuleList): List of Transformer blocks.
+            norm (RMSNorm): Layer normalization for the model output.
+            output (ColumnParallelLinear): Linear layer for final output.
+            freqs_cis (torch.Tensor): Precomputed cosine and sine frequencies.
+
+        """
+        super().__init__()
+        self.params = params
+        self.vocab_size = params.vocab_size
+        self.n_layers = params.n_layers
+
+        self.tok_embeddings = ParallelEmbedding(
+            params.vocab_size, params.dim, init_method=lambda x: x
+        )
+
+        self.layers = torch.nn.ModuleList()
+        for layer_id in range(params.n_layers):
+            self.layers.append(TransformerBlock(layer_id, params))
+
+        self.norm = RMSNorm(params.dim, eps=params.norm_eps)
+        self.output = ColumnParallelLinear(
+            params.dim, params.vocab_size, bias=False, init_method=lambda x: x
+        )
+
+        self.freqs_cis = precompute_freqs_cis(
+            # Note that self.params.max_seq_len is multiplied by 2 because the token limit for the Llama 2 generation of models is 4096. 
+            # Adding this multiplier instead of using 4096 directly allows for dynamism of token lengths while training or fine-tuning.
+            self.params.dim // self.params.n_heads, self.params.max_seq_len * 2
+        )
+
+    @torch.inference_mode()
+    def forward(self, tokens: torch.Tensor, start_pos: int):
+        """
+        Perform a forward pass through the Transformer model.
+
+        Args:
+            tokens (torch.Tensor): Input token indices.
+            start_pos (int): Starting position for attention caching.
+
+        Returns:
+            torch.Tensor: Output logits after applying the Transformer model.
+
+        """
+        _bsz, seqlen = tokens.shape
+        h = self.tok_embeddings(tokens)
+        self.freqs_cis = self.freqs_cis.to(h.device)
+        freqs_cis = self.freqs_cis[start_pos : start_pos + seqlen]
+
+        mask = None
+        if seqlen > 1:
+            mask = torch.full(
+                (seqlen, seqlen), float("-inf"), device=tokens.device
+            )
+
+            mask = torch.triu(mask, diagonal=1)
+
+            # When performing key-value caching, we compute the attention scores
+            # only for the new sequence. Thus, the matrix of scores is of size
+            # (seqlen, cache_len + seqlen), and the only masked entries are (i, j) for
+            # j > cache_len + i, since row i corresponds to token cache_len + i.
+            mask = torch.hstack([
+                torch.zeros((seqlen, start_pos), device=tokens.device),
+                mask
+            ]).type_as(h)
+
+        for layer in self.layers:
+            h = layer(h, start_pos, freqs_cis, mask)
+        h = self.norm(h)
+        output = self.output(h).float()
+        return output

tokenizer.py

@@ -0,0 +1,68 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the Llama 2 Community License Agreement.
+
+import os
+from logging import getLogger
+from typing import List
+
+from sentencepiece import SentencePieceProcessor
+
+
+logger = getLogger()
+
+
+class Tokenizer:
+    """tokenizing and encoding/decoding text using SentencePiece."""
+    def __init__(self, model_path: str):
+        """
+        Initializes the Tokenizer with a SentencePiece model.
+
+        Args:
+            model_path (str): The path to the SentencePiece model file.
+        """
+        # reload tokenizer
+        assert os.path.isfile(model_path), model_path
+        self.sp_model = SentencePieceProcessor(model_file=model_path)
+        logger.info(f"Reloaded SentencePiece model from {model_path}")
+
+        # BOS / EOS token IDs
+        self.n_words: int = self.sp_model.vocab_size()
+        self.bos_id: int = self.sp_model.bos_id()
+        self.eos_id: int = self.sp_model.eos_id()
+        self.pad_id: int = self.sp_model.pad_id()
+        logger.info(
+            f"#words: {self.n_words} - BOS ID: {self.bos_id} - EOS ID: {self.eos_id}"
+        )
+        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()
+
+    def encode(self, s: str, bos: bool, eos: bool) -> List[int]:
+        """
+        Encodes a string into a list of token IDs.
+
+        Args:
+            s (str): The input string to be encoded.
+            bos (bool): Whether to prepend the beginning-of-sequence token.
+            eos (bool): Whether to append the end-of-sequence token.
+
+        Returns:
+            List[int]: A list of token IDs.
+        """
+        assert type(s) is str
+        t = self.sp_model.encode(s)
+        if bos:
+            t = [self.bos_id] + t
+        if eos:
+            t = t + [self.eos_id]
+        return t
+
+    def decode(self, t: List[int]) -> str:
+        """
+        Decodes a list of token IDs into a string.
+
+        Args:
+            t (List[int]): The list of token IDs to be decoded.
+
+        Returns:
+            str: The decoded string.
+        """
+        return self.sp_model.decode(t)