Skip to content

Commit 02dc6a4

Browse files
authored
Merge branch 'main' into pinbump1111
2 parents bfe5826 + 4dc2f89 commit 02dc6a4

File tree

22 files changed

+1590
-262
lines changed

22 files changed

+1590
-262
lines changed

.github/workflows/pull.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -922,7 +922,7 @@ jobs:
922922
path: |
923923
./et-build
924924
./torchchat/utils/scripts
925-
key: et-build-${{runner.os}}-${{runner.arch}}-${{env.et-git-hash}}-${{ hashFiles('**/install_et.sh', '**/build_native.sh') }}
925+
key: et-build-${{runner.os}}-${{runner.arch}}-${{env.et-git-hash}}-${{ hashFiles('**/install_et.sh') }}
926926
- if: ${{ steps.install-et.outputs.cache-hit != 'true' }}
927927
continue-on-error: true
928928
run: |
@@ -1033,7 +1033,7 @@ jobs:
10331033
10341034
# Pull submodules (re2, abseil) for Tiktoken
10351035
git submodule sync
1036-
git submodule update --init --recursive
1036+
git submodule update --init
10371037
./runner/build_android.sh
10381038
echo "Tests complete."
10391039

.gitmodules

Lines changed: 9 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,9 @@
1-
[submodule "runner/third-party/tokenizers"]
2-
path = runner/third-party/tokenizers
3-
url = https://github.com/pytorch-labs/tokenizers
1+
[submodule "tokenizer/third-party/abseil-cpp"]
2+
path = tokenizer/third-party/abseil-cpp
3+
url = https://github.com/abseil/abseil-cpp.git
4+
[submodule "tokenizer/third-party/re2"]
5+
path = tokenizer/third-party/re2
6+
url = https://github.com/google/re2.git
7+
[submodule "tokenizer/third-party/sentencepiece"]
8+
path = tokenizer/third-party/sentencepiece
9+
url = https://github.com/google/sentencepiece.git

CMakeLists.txt

Lines changed: 3 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -7,21 +7,18 @@ ELSE()
77
ENDIF()
88

99
project(Torchchat)
10-
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-attributes")
1110

1211
# include tokenizer
13-
add_subdirectory(runner/third-party/tokenizers)
12+
add_subdirectory(tokenizer)
1413

1514
# include et_run executable
1615
include(runner/et.cmake)
1716
if(TARGET et_run)
18-
target_link_libraries(et_run PUBLIC tokenizers microkernels-prod)
19-
target_include_directories(et_run PUBLIC runner/third-party/tokenizers/include)
17+
target_link_libraries(et_run PUBLIC tokenizer microkernels-prod)
2018
endif()
2119

2220
# include aoti_run executable
2321
include(runner/aoti.cmake)
2422
if(TARGET aoti_run)
25-
target_link_libraries(aoti_run tokenizers)
26-
target_include_directories(aoti_run PUBLIC runner/third-party/tokenizers/include)
23+
target_link_libraries(aoti_run tokenizer)
2724
endif()

README.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -45,16 +45,16 @@ aliases.
4545

4646
| Model | Mobile Friendly | Notes |
4747
|------------------|---|---------------------|
48-
|[meta-llama/Meta-Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)||Tuned for `chat` . Alias to `llama3.2-3b`.|
48+
|[meta-llama/Meta-Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)||Tuned for `chat`. Alias to `llama3.2-3b`.|
4949
|[meta-llama/Meta-Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)||Best for `generate`. Alias to `llama3.2-3b-base`.|
50-
|[meta-llama/Llama-Guard-3-1B](https://huggingface.co/meta-llama/Llama-Guard-3-1B)||Tuned for classification . Alias to `llama3-1b-guard`.|
51-
|[meta-llama/Meta-Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)||Tuned for `chat` . Alias to `llama3.2-1b`.|
50+
|[meta-llama/Llama-Guard-3-1B](https://huggingface.co/meta-llama/Llama-Guard-3-1B)||Tuned for classification. Alias to `llama3-1b-guard`.|
51+
|[meta-llama/Meta-Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)||Tuned for `chat`. Alias to `llama3.2-1b`.|
5252
|[meta-llama/Meta-Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)||Best for `generate`. Alias to `llama3.2-1b-base`.|
53-
|[meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct)||Multimodal (Image + Text). Tuned for `chat` . Alias to `llama3.2-11B`.|
54-
|[meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision)||Multimodal (Image + Text). Tuned for `generate` . Alias to `llama3.2-11B-base`.|
55-
|[meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)||Tuned for `chat` . Alias to `llama3.1`.|
53+
|[meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct)||Multimodal (Image + Text). Tuned for `chat`. Alias to `llama3.2-11B`.|
54+
|[meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision)||Multimodal (Image + Text). Tuned for `generate`. Alias to `llama3.2-11B-base`.|
55+
|[meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)||Tuned for `chat`. Alias to `llama3.1`.|
5656
|[meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)||Best for `generate`. Alias to `llama3.1-base`.|
57-
|[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)||Tuned for `chat` . Alias to `llama3`.|
57+
|[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)||Tuned for `chat`. Alias to `llama3`.|
5858
|[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)||Best for `generate`. Alias to `llama3-base`.|
5959
|[meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)||Tuned for `chat`. Alias to `llama2`.|
6060
|[meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)||Tuned for `chat`. Alias to `llama2-13b-chat`.|
@@ -231,7 +231,7 @@ python3 torchchat.py server llama3.1
231231
```
232232
[skip default]: end
233233

234-
[shell default]: python3 torchchat.py server llama3.1 & server_pid=$!
234+
[shell default]: python3 torchchat.py server llama3.1 & server_pid=$! ; sleep 90 # wait for server to be ready to accept requests
235235

236236
In another terminal, query the server using `curl`. Depending on the model configuration, this query might take a few minutes to respond.
237237

docs/ADVANCED-USERS.md

Lines changed: 4 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,22 +1,20 @@
11
> [!WARNING]
22
> Files in this directory may be outdated, incomplete, scratch notes, or a WIP. torchchat provides no guarantees on these files as references. Please refer to the root README for stable features and documentation.
33
4-
# Torchchat is still in pre-release!
5-
6-
7-
Torchchat is currently in a pre-release state and under extensive development.
8-
94

105
# The Lost Manual: torchchat
116

127
[**Introduction**](#introduction) | [**Installation**](#installation) | [**Get Started**](#get-started) | [**Download**](#download) | [**Chat**](#chat) | [**Generate**](#generate) | [**Eval**](#eval) | [**Export**](#export) | [**Supported Systems**](#supported-systems) | [**Contributing**](#contributing) | [**License**](#license)
138

9+
<!--
10+
1411
[shell default]: HF_TOKEN="${SECRET_HF_TOKEN_PERIODIC}" huggingface-cli login
1512
1613
[shell default]: ./install/install_requirements.sh
1714
1815
[shell default]: TORCHCHAT_ROOT=${PWD} ./torchchat/utils/scripts/install_et.sh
1916
17+
-->
2018

2119
This is the advanced users' guide, if you're looking to get started
2220
with LLMs, please refer to the README at the root directory of the
@@ -465,7 +463,7 @@ significant impact on accuracy.
465463

466464
## Native (Stand-Alone) Execution of Exported Models
467465

468-
Refer to the [README](README.md] for an introduction to native
466+
Refer to the [README](README.md) for an introduction to native
469467
execution on servers, desktops, and laptops. Mobile and Edge execution for Android and iOS are
470468
described under [torchchat/edge/docs/Android.md] and [torchchat/edge/docs/iOS.md], respectively.
471469

0 commit comments

Comments
 (0)