Duplicate from chansung/LLaMA-7B

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: LLaMA 7B
+emoji: 👀
+colorFrom: indigo
+colorTo: green
+sdk: gradio
+sdk_version: 3.19.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: chansung/LLaMA-7B
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,76 @@
+import os
+import time
+import torch
+import gradio as gr
+
+from strings import TITLE, ABSTRACT 
+from gen import get_pretrained_models, get_output, setup_model_parallel
+
+os.environ["RANK"] = "0"
+os.environ["WORLD_SIZE"] = "1"
+os.environ["MASTER_ADDR"] = "127.0.0.1"
+os.environ["MASTER_PORT"] = "50505"
+
+local_rank, world_size = setup_model_parallel()
+generator = get_pretrained_models("7B", "tokenizer", local_rank, world_size)
+
+history = []
+
+def chat(user_input, top_p, temperature, max_gen_len, state_chatbot):
+    bot_response = get_output(
+        generator=generator, 
+        prompt=user_input,
+        max_gen_len=max_gen_len,
+        temperature=temperature,
+        top_p=top_p)
+
+    # remove the first phrase identical to user prompt
+    bot_response = bot_response[0][len(user_input):]
+    bot_response = bot_response.replace("\n", "<br><br>")
+    # trip the last phrase
+    try:
+        bot_response = bot_response[:bot_response.rfind(".")]
+    except:
+        pass
+
+    history.append({
+        "role": "user",
+        "content": user_input
+    })
+    history.append({
+        "role": "system",
+        "content": bot_response
+    })    
+
+    state_chatbot = state_chatbot + [(user_input, None)]
+    
+    response = ""
+    for word in bot_response.split(" "):
+        time.sleep(0.1)
+        response += word + " "
+        current_pair = (user_input, response)
+        state_chatbot[-1] = current_pair
+        yield state_chatbot, state_chatbot
+
+def reset_textbox():
+    return gr.update(value='')
+
+with gr.Blocks(css = """#col_container {width: 95%; margin-left: auto; margin-right: auto;}
+                #chatbot {height: 400px; overflow: auto;}""") as demo:
+
+    state_chatbot = gr.State([])
+                    
+    with gr.Column(elem_id='col_container'):
+        gr.Markdown(f"## {TITLE}\n\n\n\n{ABSTRACT}")
+        chatbot = gr.Chatbot(elem_id='chatbot')
+        textbox = gr.Textbox(placeholder="Enter a prompt")
+
+        with gr.Accordion("Parameters", open=False):
+            max_gen_len = gr.Slider(minimum=20, maximum=512, value=256, step=1, interactive=True, label="Max Genenration Length",)
+            top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.05, interactive=True, label="Top-p (nucleus sampling)",)
+            temperature = gr.Slider(minimum=-0, maximum=5.0, value=1.0, step=0.1, interactive=True, label="Temperature",)
+        
+    textbox.submit(chat, [textbox, top_p, temperature, max_gen_len, state_chatbot], [state_chatbot, chatbot])
+    textbox.submit(reset_textbox, [], [textbox])
+
+demo.queue(api_open=False).launch()

gen.py

@@ -0,0 +1,97 @@
+from typing import Tuple
+
+import os
+import time
+import json
+from pathlib import Path
+
+import torch
+from fairscale.nn.model_parallel.initialize import initialize_model_parallel
+from llama.generation import LLaMA
+from llama.model import ModelArgs, Transformer
+from llama.tokenizer import Tokenizer
+
+from google.cloud import storage
+
+bucket_name = os.environ.get("GCS_BUCKET")
+
+llama_weight_path = "weights/llama"
+tokenizer_weight_path = "weights/tokenizer"
+
+def setup_model_parallel() -> Tuple[int, int]:
+    local_rank = int(os.environ.get("LOCAL_RANK", -1))
+    world_size = int(os.environ.get("WORLD_SIZE", -1))
+
+    torch.distributed.init_process_group("nccl")
+    initialize_model_parallel(world_size)
+    torch.cuda.set_device(local_rank)
+
+    # seed must be the same in all processes
+    torch.manual_seed(1)
+    return local_rank, world_size
+
+def download_pretrained_models(
+    ckpt_path: str,
+    tokenizer_path: str
+):
+    os.makedirs(llama_weight_path)
+    os.makedirs(tokenizer_weight_path)
+
+    storage_client = storage.Client.create_anonymous_client()
+    bucket = storage_client.bucket(bucket_name)
+
+    blobs = bucket.list_blobs(prefix=f"{ckpt_path}/")
+    for blob in blobs:
+        filename = blob.name.split("/")[1]
+        blob.download_to_filename(f"{llama_weight_path}/{filename}")
+
+    blobs = bucket.list_blobs(prefix=f"{tokenizer_path}/")
+    for blob in blobs:
+        filename = blob.name.split("/")[1]
+        blob.download_to_filename(f"{tokenizer_weight_path}/{filename}")    
+
+def get_pretrained_models(
+    ckpt_path: str, 
+    tokenizer_path: str, 
+    local_rank: int, 
+    world_size: int) -> LLaMA:
+
+    download_pretrained_models(ckpt_path, tokenizer_path)
+
+    start_time = time.time()
+    checkpoints = sorted(Path(llama_weight_path).glob("*.pth"))
+
+    llama_ckpt_path = checkpoints[local_rank]
+    print("Loading")
+    checkpoint = torch.load(llama_ckpt_path, map_location="cpu")
+    with open(Path(llama_weight_path) / "params.json", "r") as f:
+        params = json.loads(f.read())
+
+    model_args: ModelArgs = ModelArgs(max_seq_len=512, max_batch_size=1, **params)
+    tokenizer = Tokenizer(model_path=f"{tokenizer_weight_path}/tokenizer.model")
+    model_args.vocab_size = tokenizer.n_words
+    torch.set_default_tensor_type(torch.cuda.HalfTensor)
+    model = Transformer(model_args).cuda().half()
+    torch.set_default_tensor_type(torch.FloatTensor)
+    model.load_state_dict(checkpoint, strict=False)
+
+    generator = LLaMA(model, tokenizer)
+    print(f"Loaded in {time.time() - start_time:.2f} seconds")
+    return generator
+
+def get_output(
+    generator: LLaMA,
+    prompt: str,
+    max_gen_len: int = 256,
+    temperature: float = 0.8, 
+    top_p: float = 0.95):
+    
+    prompts = [prompt]
+    results = generator.generate(
+        prompts, 
+        max_gen_len=max_gen_len, 
+        temperature=temperature, 
+        top_p=top_p
+    )
+
+    return results

llama/generation.py

@@ -0,0 +1,77 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the GNU General Public License version 3.
+
+from typing import List
+
+import torch
+
+from llama.tokenizer import Tokenizer
+from llama.model import Transformer
+
+
+class LLaMA:
+    def __init__(self, model: Transformer, tokenizer: Tokenizer):
+        self.model = model
+        self.tokenizer = tokenizer
+
+    def generate(
+        self,
+        prompts: List[str],
+        max_gen_len: int,
+        temperature: float = 0.8,
+        top_p: float = 0.95,
+    ) -> List[str]:
+        bsz = len(prompts)
+        params = self.model.params
+        assert bsz <= params.max_batch_size, (bsz, params.max_batch_size)
+
+        prompt_tokens = [self.tokenizer.encode(x, bos=True, eos=False) for x in prompts]
+
+        min_prompt_size = min([len(t) for t in prompt_tokens])
+        max_prompt_size = max([len(t) for t in prompt_tokens])
+
+        total_len = min(params.max_seq_len, max_gen_len + max_prompt_size)
+
+        tokens = torch.full((bsz, total_len), self.tokenizer.pad_id).cuda().long()
+        for k, t in enumerate(prompt_tokens):
+            tokens[k, : len(t)] = torch.tensor(t).long()
+        input_text_mask = tokens != self.tokenizer.pad_id
+        start_pos = min_prompt_size
+        prev_pos = 0
+        for cur_pos in range(start_pos, total_len):
+            logits = self.model.forward(tokens[:, prev_pos:cur_pos], prev_pos)
+            if temperature > 0:
+                probs = torch.softmax(logits / temperature, dim=-1)
+                next_token = sample_top_p(probs, top_p)
+            else:
+                next_token = torch.argmax(logits, 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
+            prev_pos = cur_pos
+
+        decoded = []
+        for i, t in enumerate(tokens.tolist()):
+            # cut to max gen len
+            t = t[: len(prompt_tokens[i]) + max_gen_len]
+            # cut to eos tok if any
+            try:
+                t = t[: t.index(self.tokenizer.eos_id)]
+            except ValueError:
+                pass
+            decoded.append(self.tokenizer.decode(t))
+        return decoded
+
+
+def sample_top_p(probs, p):
+    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

llama/model.py

@@ -0,0 +1,238 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the GNU General Public License version 3.
+
+from typing import Optional, Tuple
+from dataclasses import dataclass
+import math
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import fairscale.nn.model_parallel.initialize as fs_init
+from fairscale.nn.model_parallel.layers import (
+    ParallelEmbedding,
+    RowParallelLinear,
+    ColumnParallelLinear,
+)
+
+
+@dataclass
+class ModelArgs:
+    dim: int = 512
+    n_layers: int = 8
+    n_heads: int = 8
+    vocab_size: int = -1  # defined later by tokenizer
+    multiple_of: int = 256  # make SwiGLU hidden layer size multiple of large power of 2
+    norm_eps: float = 1e-5
+
+    max_batch_size: int = 32
+    max_seq_len: int = 1024
+
+
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def _norm(self, x):
+        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
+
+    def forward(self, x):
+        output = self._norm(x.float()).type_as(x)
+        return output * self.weight
+
+
+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)  # 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):
+    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]:
+    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)
+
+
+class Attention(nn.Module):
+    def __init__(self, args: ModelArgs):
+        super().__init__()
+
+        self.n_local_heads = args.n_heads // fs_init.get_model_parallel_world_size()
+        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,
+            args.n_heads * self.head_dim,
+            bias=False,
+            gather_output=False,
+            init_method=lambda x: x,
+        )
+        self.wv = ColumnParallelLinear(
+            args.dim,
+            args.n_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_heads, self.head_dim)
+        ).cuda()
+        self.cache_v = torch.zeros(
+            (args.max_batch_size, args.max_seq_len, self.n_local_heads, self.head_dim)
+        ).cuda()
+
+    def forward(self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor]):
+        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_heads, self.head_dim)
+        xv = xv.view(bsz, seqlen, self.n_local_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]
+
+        xq = xq.transpose(1, 2)
+        keys = keys.transpose(1, 2)
+        values = values.transpose(1, 2)
+        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, slen, cache_len + slen)
+        scores = F.softmax(scores.float(), dim=-1).type_as(xq)
+        output = torch.matmul(scores, values)  # (bs, n_local_heads, slen, 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,
+    ):
+        super().__init__()
+        hidden_dim = int(2 * hidden_dim / 3)
+        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):
+        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
+        )
+        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]):
+        h = x + self.attention.forward(self.attention_norm(x), start_pos, freqs_cis, mask)
+        out = h + self.feed_forward.forward(self.ffn_norm(h))
+        return out
+
+
+class Transformer(nn.Module):
+    def __init__(self, params: ModelArgs):
+        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(
+            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):
+        _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((1, 1, seqlen, seqlen), float("-inf"), device=tokens.device)
+            mask = torch.triu(mask, diagonal=start_pos + 1).type_as(h)
+
+        for layer in self.layers:
+            h = layer(h, start_pos, freqs_cis, mask)
+        h = self.norm(h)
+        output = self.output(h[:, -1, :])  # only compute last logits
+        return output.float()

llama/tokenizer.py

@@ -0,0 +1,40 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# This software may be used and distributed according to the terms of the GNU General Public License version 3.
+
+from sentencepiece import SentencePieceProcessor
+from logging import getLogger
+from typing import List
+import os
+
+
+logger = getLogger()
+
+
+class Tokenizer:
+    def __init__(self, model_path: str):
+        # 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]:
+        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:
+        return self.sp_model.decode(t)

requirements.txt

@@ -0,0 +1,4 @@
+torch
+fairscale
+sentencepiece
+google-cloud-storage

strings.py

@@ -0,0 +1,7 @@
+TITLE = "LLaMA 7B Model Playground"
+
+ABSTRACT = """
+This Space allows you to play with the one of the variant(7B) as part of the [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/)(Large Language Model Meta AI) released by Meta AI. 
+
+LLaMA is a general purpose language model, so it behaves differently comparing to [ChatGPT](https://openai.com/blog/chatgpt/). Even though the UI or this Space application is in Chat-like form, the generated output will be the completion of the given prompt. Because of this, your prompts should appropriately guide what to be generated.
+"""