Llama 3.1

    num_reserved_special_tokens = 256

    pat_str = r"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"  # noqa: E501

… lines 48–55 omitted …

        assert os.path.isfile(model_path), model_path

        mergeable_ranks = load_tiktoken_bpe(model_path)
        num_base_tokens = len(mergeable_ranks)
        special_tokens = [
            "<|begin_of_text|>",
            "<|end_of_text|>",
            "<|reserved_special_token_0|>",
            "<|reserved_special_token_1|>",
            "<|reserved_special_token_2|>",
            "<|reserved_special_token_3|>",
            "<|start_header_id|>",
            "<|end_header_id|>",
            "<|reserved_special_token_4|>",
            "<|eot_id|>",  # end of turn
        ] + [
            f"<|reserved_special_token_{i}|>"
            for i in range(5, self.num_reserved_special_tokens - 5)
        ]
        self.special_tokens = {
            token: num_base_tokens + i for i, token in enumerate(special_tokens)
        }
        self.model = tiktoken.Encoding(
            name=Path(model_path).name,
            pat_str=self.pat_str,
            mergeable_ranks=mergeable_ranks,
            special_tokens=self.special_tokens,
        )

… lines 84–146 omitted …

        t: List[int] = []
        for substr in substrs:
            t.extend(
                self.model.encode(
                    substr,
                    allowed_special=allowed_special,
                    disallowed_special=disallowed_special,
                )
            )
        if bos:
            t.insert(0, self.bos_id)
        if eos:
            t.append(self.eos_id)
        return t

        prompt_tokens = [self.tokenizer.encode(x, bos=True, eos=False) for x in prompts]

LLAMA3_VOCAB_SIZE = 128256

… lines 20–230 omitted …

        Model(
            core_model_id=CoreModelId.llama3_1_8b,
            description="Llama 3.1 8b model",
            huggingface_repo="meta-llama/Llama-3.1-8B",
            arch_args={
                "dim": 4096,
                "n_layers": 32,
                "n_heads": 32,
                "n_kv_heads": 8,
                "vocab_size": LLAMA3_VOCAB_SIZE,
                "ffn_dim_multiplier": 1.3,
                "multiple_of": 1024,
                "norm_eps": 1e-05,
                "rope_theta": 500000.0,
                "use_scaled_rope": True,
            },
            pth_file_count=1,
        ),

        super().__init__()
        self.params = params
        self.vocab_size = params.vocab_size
        self.n_layers = params.n_layers

        self.tok_embeddings = VocabParallelEmbedding(
            params.vocab_size, params.dim, init_method=lambda x: x
        )

… lines 261–278 omitted …

        _bsz, seqlen = tokens.shape
        h = self.tok_embeddings(tokens)

        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)

… lines 267–297 omitted …

        for layer in self.layers:
            h = layer(h, start_pos, freqs_cis, mask)
        h = self.norm(h)

        self.norm = RMSNorm(params.dim, eps=params.norm_eps)
        self.output = ColumnParallelLinear(
            params.dim, params.vocab_size, bias=False, init_method=lambda x: x
        )

… lines 270–297 omitted …

        for layer in self.layers:
            h = layer(h, start_pos, freqs_cis, mask)
        h = self.norm(h)
        output = self.output(h).float()
        return output

def precompute_freqs_cis(dim: int, end: int, theta: float = 10000.0):
    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim))
    t = torch.arange(end, device=freqs.device, dtype=torch.float32)
    freqs = torch.outer(t, freqs)
    freqs_cis = torch.polar(torch.ones_like(freqs), freqs)  # complex64
    return freqs_cis

… lines 55–270 omitted …

        self.freqs_cis = precompute_freqs_cis(
            params.dim // params.n_heads,
            params.max_seq_len * 2,
            params.rope_theta,
        )

    @torch.inference_mode()
    def forward(self, tokens: torch.Tensor, start_pos: int):
        _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)