add grop ande change to 24.04

.gitignore

+checkpoints/*
+!checkpoints/README.md

CODE_OF_CONDUCT.md

+Be excellent to each other.

Contributors.md

+# Contributors
+None

LICENSE.txt

+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

+# Grok1
+Grok-1是由xAI从头开始训练的3140亿个参数混合专家模型。
+
+## 论文
+暂无
+
+## 模型结构
+Grok-1 是一个8个专家（2个活跃）的混合专家（MoE）模型。
+<div align=center>
+    <img src="./doc/MoE.png"/>
+</div>
+
+## 算法原理
+Grok-1目前的设计规格如下:
+- **参数:** 314B
+- **体系结构:** Mixture of 8 Experts (MoE)
+- **专家利用:** 2 experts used per token
+- **层数:** 64
+- **多头注意力:** 48 个 head 用于查询，8 个用于键 / 值（KV）
+- **嵌入大小:** 6,144
+- **Tokenization:** tokenizer 词汇大小为 131,072
+- **附加特性:**
+  - Rotary embeddings (RoPE)
+  - Supports activation sharding and 8-bit 量化
+- **最大序列长度(上下文):** 8,192 tokens
+
+## 环境配置
+### Docker（方法一）
+-v 路径、docker_name和imageID根据实际情况修改
+
+```bash
+docker pull image.sourcefind.cn:5000/dcu/admin/base/jax:0.4.23-ubuntu20.04-dtk24.04-py310
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --shm-size=200G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/grok-1_jax
+pip install -r requirements.txt
+```
+
+### Dockerfile（方法二）
+```bash
+cd ./docker
+docker build --no-cache -t grok1:latest .
+
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal:ro --shm-size=200G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/grok-1_jax
+```
+
+### Anaconda（方法三）
+关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
+
+```
+DTK驱动：dtk24.04
+python：python3.10
+jax: ≥ 0.4.23
+gcc: ≥ 9.4.0
+```
+`Tips：以上dtk驱动、python等DCU相关工具版本需要严格一一对应`
+
+其它非深度学习库参照requirements.txt安装：
+```bash
+pip install -r requirements.txt
+```
+
+## 数据集
+暂无
+
+## 训练
+官方github未开源微调代码
+
+## 推理
+推理所需硬件最低配置参考：
+
+device(s)：K100 64G 8卡
+
+Driver version: 5.16.29.22.20
+
+Vbios version: 5.223.001200k.548101
+
+linux: ubuntu20.04
+
+处理器： Hygon C86 7375 32-core Processor
+
+CPU(s)：128
+
+内存：≥ 600G, 1T以上最优
+
+```bash
+python run.py
+```
+
+## result
+日志信息可以参考**log.txt**文件
+
+<div align=center>
+    <img src="./doc/end.png"/>
+</div>
+
+### 精度
+暂无
+
+## 应用场景
+### 算法类别
+对话问答
+
+### 热点应用行业
+制造,广媒,家居,教育
+
+## 预训练权重
+下载地址[huggingface_grok-1](https://hf-mirror.com/xai-org/grok-1)
+
+也可以直接使用`./checkpoints/down_models.py`进行下载，模型默认保存地址为：`~/.cache/modelscope/hub/cjc1887415157/grok-1/`。
+
+```bash
+python ./checkpoints/down_models.py
+mv ~/.cache/modelscope/hub/cjc1887415157/grok-1/ckpt-0 ./
+```
+
+## 源码仓库及问题反馈
+- https://developer.hpccube.com/codes/modelzoo/grok-1_jax
+
+## 参考资料
+- https://github.com/xai-org/grok-1

README_ori.md

+# Grok-1
+
+
+
+image.sourcefind.cn:5000/dcu/admin/base/tensorflow:2.11.0-ubuntu20.04-dtk23.10-py310
+
+
+
+This repository contains JAX example code for loading and running the Grok-1 open-weights model.
+
+Make sure to download the checkpoint and place the `ckpt-0` directory in `checkpoints` - see [Downloading the weights](#downloading-the-weights)
+
+Then, run
+
+```shell
+pip install -r requirements.txt
+python run.py
+```
+
+to test the code.
+
+The script loads the checkpoint and samples from the model on a test input.
+
+Due to the large size of the model (314B parameters), a machine with enough GPU memory is required to test the model with the example code.
+The implementation of the MoE layer in this repository is not efficient. The implementation was chosen to avoid the need for custom kernels to validate the correctness of the model.
+
+# Model Specifications
+
+Grok-1 is currently designed with the following specifications:
+
+- **Parameters:** 314B
+- **Architecture:** Mixture of 8 Experts (MoE)
+- **Experts Utilization:** 2 experts used per token
+- **Layers:** 64
+- **Attention Heads:** 48 for queries, 8 for keys/values
+- **Embedding Size:** 6,144
+- **Tokenization:** SentencePiece tokenizer with 131,072 tokens
+- **Additional Features:**
+  - Rotary embeddings (RoPE)
+  - Supports activation sharding and 8-bit quantization
+- **Maximum Sequence Length (context):** 8,192 tokens
+
+# Downloading the weights
+
+You can download the weights using a torrent client and this magnet link:
+
+```
+magnet:?xt=urn:btih:5f96d43576e3d386c9ba65b883210a393b68210e&tr=https%3A%2F%2Facademictorrents.com%2Fannounce.php&tr=udp%3A%2F%2Ftracker.coppersurfer.tk%3A6969&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce
+```
+
+or directly using [HuggingFace 🤗 Hub](https://huggingface.co/xai-org/grok-1):
+```
+git clone https://github.com/xai-org/grok-1.git && cd grok-1
+pip install huggingface_hub[hf_transfer]
+huggingface-cli download xai-org/grok-1 --repo-type model --include ckpt-0/* --local-dir checkpoints --local-dir-use-symlinks False
+```
+
+# License
+
+The code and associated Grok-1 weights in this release are licensed under the
+Apache 2.0 license. The license only applies to the source files in this
+repository and the model weights of Grok-1.

checkpoint.py

+# Copyright 2024 X.AI Corp.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import contextlib
+import logging
+import math
+import os
+import pickle
+import re
+import shutil
+import sys
+import tempfile
+from concurrent.futures import ThreadPoolExecutor, wait
+from typing import Any, Optional
+
+import jax
+import numpy as np
+from jax.experimental import multihost_utils
+
+from model import QuantizedWeight8bit
+
+logger = logging.getLogger(__name__)
+rank_logger = logging.getLogger("rank")
+
+# Needed for loading the checkpoint with pickle.
+sys.modules['__main__'].QuantizedWeight8bit = QuantizedWeight8bit
+
+
+@contextlib.contextmanager
+def copy_to_shm(file: str):
+    if file.startswith("/dev/shm/"):
+        # Nothing to do, the file is already in shared memory.
+        yield file
+        return
+
+    tmp_dir = "/dev/shm/"
+    fd, tmp_path = tempfile.mkstemp(dir=tmp_dir)
+    try:
+        shutil.copyfile(file, tmp_path)
+        yield tmp_path
+    finally:
+        os.remove(tmp_path)
+        os.close(fd)
+
+
+@contextlib.contextmanager
+def copy_from_shm(file: str):
+    tmp_dir = "/dev/shm/"
+    fd, tmp_path = tempfile.mkstemp(dir=tmp_dir)
+    try:
+        yield tmp_path
+        shutil.copyfile(tmp_path, file)
+    finally:
+        os.remove(tmp_path)
+        os.close(fd)
+
+
+# def fast_unpickle(path: str) -> Any:
+#     with copy_to_shm(path) as tmp_path:
+#         with open(tmp_path, "rb") as f:
+#             return pickle.load(f)
+
+
+def fast_unpickle(path: str) -> Any:
+    with open(path, "rb") as f:
+        return pickle.load(f)
+
+
+def fast_pickle(obj: Any, path: str) -> None:
+    with copy_from_shm(path) as tmp_path:
+        with open(tmp_path, "wb") as f:
+            pickle.dump(obj, f)
+
+
+def load_tensors(shaped_arrays, directory, mesh_config, tensor_indices=None):
+    """Loads a set of arrays."""
+    pool = ThreadPoolExecutor(max_workers=32)
+    fs = list()
+    num_tensors = 0
+    num_replicas = 1
+    data_model_shards = math.prod(mesh_config)
+    if tensor_indices is None:
+        iterator = enumerate(shaped_arrays)
+    else:
+        iterator = zip(tensor_indices, shaped_arrays)
+    for i, t in iterator:
+        if (i % num_replicas) == ((jax.process_index() // data_model_shards) % num_replicas):
+            idx = (
+                jax.process_index() // (num_replicas * data_model_shards) * data_model_shards
+                + jax.process_index() % data_model_shards
+            )
+            fs.append(
+                pool.submit(fast_unpickle, os.path.join(directory, f"tensor{i:05d}_{idx:03d}"))
+            )
+            num_tensors += 1
+        else:
+            fs.append(pool.submit(np.zeros, t.shape, dtype=t.dtype))
+    wait(fs)
+    return [f.result() for f in fs]
+
+
+def path_tuple_to_string(path: tuple) -> str:
+    pieces = []
+    for elem in path:
+        if isinstance(elem, jax.tree_util.DictKey):
+            pieces.append(elem.key)
+        elif isinstance(elem, jax.tree_util.GetAttrKey):
+            pieces.append(elem.name)
+        else:
+            assert isinstance(elem, (jax.tree_util.FlattenedIndexKey, jax.tree_util.SequenceKey))
+    return "/".join(pieces)
+
+
+def get_load_path_str(
+    init_path_str: str,
+    load_rename_rules: Optional[list[tuple[str, str]]] = None,
+    load_exclude_rules: Optional[list[str]] = None,
+) -> Optional[str]:
+    # Exclusion
+    if load_exclude_rules is not None:
+        for search_pattern in load_exclude_rules:
+            if re.search(search_pattern, init_path_str):
+                return None
+
+    # Renaming
+    load_path_str = init_path_str
+    if load_rename_rules is not None:
+        for search_pattern, replacement_pattern in load_rename_rules:
+            if re.search(search_pattern, load_path_str):
+                load_path_str = re.sub(search_pattern, replacement_pattern, load_path_str)
+                break
+
+    return load_path_str
+
+
+def replace_with_load_state(
+    init_state: Any,
+    load_state: Any,
+    load_rename_rules: Optional[list[tuple[str, str]]] = None,
+    load_exclude_rules: Optional[list[str]] = None,
+    mesh_config: tuple = (1, 1),
+) -> Any:
+    flatten_load, _ = jax.tree_util.tree_flatten_with_path(load_state)
+    flatten_init, structure_init = jax.tree_util.tree_flatten_with_path(init_state)
+    load_map = {path_tuple_to_string(path): tensor for path, tensor in flatten_load}
+
+    replaced = []
+    num_replicas = 1
+    data_model_shards = math.prod(mesh_config)
+    for i, (init_path, tensor) in enumerate(flatten_init):
+        init_path_str = path_tuple_to_string(init_path)
+        load_path_str = get_load_path_str(init_path_str, load_rename_rules, load_exclude_rules)
+        if load_path_str is None:
+            rank_logger.info(f"Excluded from restore: {init_path_str}.")
+            replaced.append(tensor)
+        elif load_path_str in load_map:
+            if load_path_str == init_path_str:
+                rank_logger.info(f"Restored from ckpt: {init_path_str}.")
+            else:
+                rank_logger.info(f"Restored from ckpt: {init_path_str} <-- {load_path_str}.")
+            replaced.append(load_map[load_path_str])
+        else:
+            rank_logger.info(f"Not found in ckpt: {init_path_str}.")
+            if (i % num_replicas) == ((jax.process_index() // data_model_shards) % num_replicas):
+                replaced.append(tensor)
+            else:
+                replaced.append(np.zeros_like(tensor))
+
+    return jax.tree_util.tree_unflatten(structure_init, replaced)
+
+
+def restore(
+    checkpoint_path: str,
+    state_shapes: Any,
+    mesh,
+    between_hosts_config,
+    params_only,
+    state_sharding,
+    init_state: Optional[Any] = None,
+) -> Any:
+    ckpt_path = os.path.join(checkpoint_path, "ckpt-0")
+
+    rank_logger.info("Loading checkpoint at {}".format(ckpt_path))
+    ckpt_shapes = state_shapes
+    ckpt_shapes_with_path, structure = jax.tree_util.tree_flatten_with_path(ckpt_shapes)
+
+    ckpt_shapes_flat = [elem[1] for elem in ckpt_shapes_with_path]
+    loaded_tensors = load_tensors(ckpt_shapes_flat, ckpt_path, between_hosts_config)
+
+    state = jax.tree_util.tree_unflatten(structure, loaded_tensors)
+
+    # Sanity check to give a better error message.
+    ckpt_keys = set(state.params.keys())
+    code_keys = set(state_sharding.params.keys())
+
+    if ckpt_keys != code_keys and init_state is None:
+        missing_in_ckpt = code_keys - ckpt_keys
+        missing_locally = ckpt_keys - code_keys
+        raise ValueError(
+            "Parameters in the code are not matching checkpoint parameters.\n"
+            "Params missing in checkpoint: {}\nParams missing in code: {}".format(
+                missing_in_ckpt, missing_locally
+            )
+        )
+    state_sharding = jax.tree_util.tree_map(
+        lambda x: jax.sharding.PartitionSpec() if x is None else x,
+        state_sharding,
+        is_leaf=lambda x: x is None,
+    )
+    state = multihost_utils.host_local_array_to_global_array(state, mesh, state_sharding)
+    if params_only:
+        state = state.params
+    return state

checkpoints/README.md

+# Checkpoint directory
+
+Place Grok-1 checkpoints here so they can be loaded by the example script.

debug.log

+[0403/192602.428:INFO:skin_prom_main.cpp(112)] skinprom start
+[0403/192603.240:INFO:skin_prom_main.cpp(137)] skinprom end

docker/Dockerfile

+FROM docker pull image.sourcefind.cn:5000/dcu/admin/base/jax:0.4.23-ubuntu20.04-dtk24.04-py310

model.properties

+# 模型唯一标识
+modelCode=571
+# 模型名称
+modelName=grok-1_jax
+# 模型描述
+modelDescription=Grok-1是由xAI从头开始训练的3140亿个参数混合专家模型。
+# 应用场景
+appScenario=推理,对话问答,制造,广媒,家居,教育
+# 框架类型
+frameType=jax

pyproject.toml

+[tool.ruff]
+indent-width = 4
+line-length = 100
+
+[tool.ruff.lint]
+ignore = [
+    "E722",
+    "E731",
+    "E741",
+    "F405",
+    "E402",
+    "F403",
+]
+select = ["ISC001"]

requirements.txt

+dm_haiku==0.0.12
+sentencepiece==0.2.0

run.py

+# Copyright 2024 X.AI Corp.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import time
+import logging
+
+from model import LanguageModelConfig, TransformerConfig, QuantizedWeight8bit as QW8Bit
+from runners import InferenceRunner, ModelRunner, sample_from_model
+
+
+CKPT_PATH = "./checkpoints/"
+
+
+def main():
+    grok_1_model = LanguageModelConfig(
+        vocab_size=128 * 1024,
+        pad_token=0,
+        eos_token=2,
+        sequence_len=8192,
+        embedding_init_scale=1.0,
+        output_multiplier_scale=0.5773502691896257,
+        embedding_multiplier_scale=78.38367176906169,
+        model=TransformerConfig(
+            emb_size=48 * 128,
+            widening_factor=8,
+            key_size=128,
+            num_q_heads=48,
+            num_kv_heads=8,
+            num_layers=64,
+            attn_output_multiplier=0.08838834764831845,
+            shard_activations=True,
+            # MoE.
+            num_experts=8,
+            num_selected_experts=2,
+            # Activation sharding.
+            data_axis="data",
+            model_axis="model",
+        ),
+    )
+    inference_runner = InferenceRunner(
+        pad_sizes=(1024,),
+        runner=ModelRunner(
+            model=grok_1_model,
+            bs_per_device=0.125,
+            checkpoint_path=CKPT_PATH,
+        ),
+        name="local",
+        load=CKPT_PATH,
+        tokenizer_path="./tokenizer.model",
+        local_mesh_config=(1, 8),
+        between_hosts_config=(1, 1),
+    )
+    inference_runner.initialize()
+    start_time = time.time()
+    gen = inference_runner.run()
+    print("infer time：", time.time() - start_time, "秒")
+
+    inp = "The answer to life the universe and everything is of course"
+    print(f"Output for prompt: {inp}", sample_from_model(gen, inp, max_len=100, temperature=0.01))
+
+
+if __name__ == "__main__":
+    logging.basicConfig(level=logging.INFO)
+    main()