From 78bcb07f0ecd0b57d349dc6ffdf199a4632245ca Mon Sep 17 00:00:00 2001 From: Yuzhe Gu <74947293+Liqu1d-G@users.noreply.github.com> Date: Fri, 26 Jan 2024 17:26:04 +0800 Subject: [PATCH] [CI]: fix and pass pre-commit hook (#666) --- .github/workflows/daily_tests.yaml | 4 +- .github/workflows/lint_check.yaml | 12 -- .pre-commit-config.yaml | 81 +++++------ README.md | 86 +++++------ README_zh-CN.md | 85 +++++------ agent/README.md | 14 +- agent/README_zh-CN.md | 12 +- agent/lagent_zh-CN.md | 2 +- agent/pal_inference.md | 29 ++-- agent/pal_inference.py | 221 +++++++++++++++++------------ agent/pal_inference_zh-CN.md | 29 ++-- chat/chat_format.md | 12 +- chat/chat_format_zh-CN.md | 15 +- chat/lmdeploy.md | 1 - chat/lmdeploy_zh_cn.md | 2 +- chat/openaoe.md | 25 +++- chat/openaoe_zh_cn.md | 30 +++- chat/web_demo.py | 197 ++++++++++++++----------- finetune/README.md | 2 +- finetune/README_zh-CN.md | 2 +- model_cards/internlm2_20b.md | 31 ++-- model_cards/internlm2_7b.md | 32 ++--- model_cards/internlm_20b.md | 62 ++++---- model_cards/internlm_7b.md | 34 ++--- requirements.txt | 2 +- tests/test_hf_model.py | 59 ++++---- tools/README.md | 1 + tools/convert2llama.py | 101 ++++++------- 28 files changed, 637 insertions(+), 546 deletions(-) diff --git a/.github/workflows/daily_tests.yaml b/.github/workflows/daily_tests.yaml index 2bc64dd..d088c96 100644 --- a/.github/workflows/daily_tests.yaml +++ b/.github/workflows/daily_tests.yaml @@ -26,8 +26,8 @@ jobs: pip install transformers pip install sentencepiece srun -p ${SLURM_PARTITION} --kill-on-bad-exit=1 --job-name=${GITHUB_RUN_ID}-${GITHUB_JOB} --gpus-per-task=2 pytest -s -v --color=yes ./tests/test_hf_model.py - conda deactivate - + conda deactivate + clear_env: if: ${{ !cancelled() }} needs: [HF_model] diff --git a/.github/workflows/lint_check.yaml b/.github/workflows/lint_check.yaml index e661e80..ed042f4 100644 --- a/.github/workflows/lint_check.yaml +++ b/.github/workflows/lint_check.yaml @@ -24,15 +24,3 @@ jobs: run: | pip install isort==5.12.0 isort --check --profile=black . - - - name: lint-black - run: | - pip install black==22.8.0 - BLACK_EXCLUDE_SETTINGS='\.venv/|\.local/|\.cache/|\.git/' - black --line-length=120 --check --exclude $BLACK_EXCLUDE_SETTINGS ./chat/web_demo.py - - - name: lint-pylint - run: | - pip install pylint==v2.17.2 - PYLINT_DISABLE_LIST="C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203" - pylint --rcfile .pylintrc --disable=$PYLINT_DISABLE_LIST ./chat/web_demo.py diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 8a43efd..6f29f08 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,53 +1,44 @@ -# See https://pre-commit.com for more information -# See https://pre-commit.com/hooks.html for more hooks repos: -- repo: https://github.com/psf/black - rev: '22.8.0' + - repo: https://github.com/PyCQA/flake8 + rev: 5.0.4 hooks: - - id: black - args: - - --line-length=120 -- repo: https://github.com/pycqa/isort - rev: '5.12.0' + - id: flake8 + - repo: https://github.com/PyCQA/isort + rev: 5.11.5 hooks: - - id: isort - name: isort - files: "\\.(py)$" - args: - - --profile=black -- repo: https://github.com/PyCQA/flake8 - rev: '3.8.4' + - id: isort + - repo: https://github.com/pre-commit/mirrors-yapf + rev: v0.32.0 hooks: - - id: flake8 - args: - - --ignore=F403,F405,W504,W503,E203 - - --max-line-length=120 -- repo: https://github.com/pre-commit/pygrep-hooks - rev: v1.9.0 + - id: yapf + - repo: https://github.com/codespell-project/codespell + rev: v2.2.1 hooks: - - id: python-check-blanket-noqa -- repo: https://github.com/pre-commit/pre-commit-hooks + - id: codespell + - repo: https://github.com/pre-commit/pre-commit-hooks rev: v4.3.0 hooks: - - id: trailing-whitespace - - id: end-of-file-fixer - - id: check-added-large-files - args: ['--maxkb=100',--enforce-all] - - id: check-json - - id: check-docstring-first - - id: check-yaml - - id: debug-statements - - id: mixed-line-ending -- repo: https://github.com/PyCQA/pylint/ - rev: v2.17.2 + - id: trailing-whitespace + - id: check-yaml + - id: end-of-file-fixer + - id: requirements-txt-fixer + - id: double-quote-string-fixer + - id: check-merge-conflict + - id: fix-encoding-pragma + args: ["--remove"] + - id: mixed-line-ending + args: ["--fix=lf"] + - repo: https://github.com/executablebooks/mdformat + rev: 0.7.9 hooks: - - id: pylint - name: pylint - entry: pylint - language: system - types: [python] - args: - [ - '--rcfile=.pylintrc', - '--disable=C0114,C0415,W0212,W0235,W0238,W0621,C0103,R1735,C2801,E0402,C0412,W0719,R1728,W1514,W0718,W0105,W0707,C0209,W0703,W1203' - ] + - id: mdformat + args: ["--number", "--table-width", "200"] + additional_dependencies: + - mdformat-openmmlab + - mdformat_frontmatter + - linkify-it-py + - repo: https://github.com/myint/docformatter + rev: v1.3.1 + hooks: + - id: docformatter + args: ["--in-place", "--wrap-descriptions", "79"] diff --git a/README.md b/README.md index da3ed09..bfb84d0 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,9 @@ [![license](./assets/license.svg)](./LICENSE) [![evaluation](./assets/compass_support.svg)](https://github.com/internLM/OpenCompass/) + + [📘Commercial Application](#license) | [🤗HuggingFace](https://huggingface.co/internlm) | [🆕Update News](#news) | @@ -45,26 +47,26 @@ InternLM2 series are released with the following features: ## News -[2024.01.23] We release InternLM2-Math-7B and InternLM2-Math-20B with pretraining and SFT checkpoints. They surpass ChatGPT with small sizes. See [InternLM-Math](https://github.com/InternLM/internlm-math) for details and download. +\[2024.01.23\] We release InternLM2-Math-7B and InternLM2-Math-20B with pretraining and SFT checkpoints. They surpass ChatGPT with small sizes. See [InternLM-Math](https://github.com/InternLM/internlm-math) for details and download. -[2024.01.17] We release InternLM2-7B and InternLM2-20B and their corresponding chat models with stronger capabilities in all dimensions. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details. +\[2024.01.17\] We release InternLM2-7B and InternLM2-20B and their corresponding chat models with stronger capabilities in all dimensions. See [model zoo below](#model-zoo) for download or [model cards](./model_cards/) for more details. -[2023.12.13] InternLM-7B-Chat and InternLM-20B-Chat checkpoints are updated. With an improved finetuning strategy, the new chat models can generate higher quality responses with greater stylistic diversity. +\[2023.12.13\] InternLM-7B-Chat and InternLM-20B-Chat checkpoints are updated. With an improved finetuning strategy, the new chat models can generate higher quality responses with greater stylistic diversity. -[2023.09.20] InternLM-20B is released with base and chat versions. +\[2023.09.20\] InternLM-20B is released with base and chat versions. ## Model Zoo -| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date | -|---------------------------|------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------| -| **InternLM2-Base-7B** | [🤗internlm2-base-7b](https://huggingface.co/internlm/internlm2-base-7b) | [ internlm2-base-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b-original) | 2024-01-17 | -| **InternLM2-7B** | [🤗internlm2-7b](https://huggingface.co/internlm/internlm2-7b) | [ internlm2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b-original) | 2024-01-17 | -| **InternLM2-Chat-7B-SFT** | [🤗internlm2-chat-7b-sft](https://huggingface.co/internlm/internlm2-chat-7b-sft) | [ internlm2-chat-7b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft-original) | 2024-01-17 | -| **InternLM2-Chat-7B** | [🤗internlm2-chat-7b](https://huggingface.co/internlm/internlm2-chat-7b) | [ internlm2-chat-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-original) | 2024-01-17 | -| **InternLM2-Base-20B** | [🤗internlm2-base-20b](https://huggingface.co/internlm/internlm2-base-20b) | [ internlm2-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b-original) | 2024-01-17 | -| **InternLM2-20B** | [🤗internlm2-20b](https://huggingface.co/internlm/internlm2-20b) | [ internlm2-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b-original) | 2024-01-17 | -| **InternLM2-Chat-20B-SFT** | [🤗internlm2-chat-20b-sft](https://huggingface.co/internlm/internlm2-chat-20b-sft) | [ internlm2-chat-20b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft-original) | 2024-01-17 | -| **InternLM2-Chat-20B** | [🤗internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b) | [ internlm2-chat-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-original) | 2024-01-17 | +| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date | +| -------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ | +| **InternLM2-Base-7B** | [🤗internlm2-base-7b](https://huggingface.co/internlm/internlm2-base-7b) | [ internlm2-base-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b-original) | 2024-01-17 | +| **InternLM2-7B** | [🤗internlm2-7b](https://huggingface.co/internlm/internlm2-7b) | [ internlm2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b-original) | 2024-01-17 | +| **InternLM2-Chat-7B-SFT** | [🤗internlm2-chat-7b-sft](https://huggingface.co/internlm/internlm2-chat-7b-sft) | [ internlm2-chat-7b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft-original) | 2024-01-17 | +| **InternLM2-Chat-7B** | [🤗internlm2-chat-7b](https://huggingface.co/internlm/internlm2-chat-7b) | [ internlm2-chat-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-original) | 2024-01-17 | +| **InternLM2-Base-20B** | [🤗internlm2-base-20b](https://huggingface.co/internlm/internlm2-base-20b) | [ internlm2-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b-original) | 2024-01-17 | +| **InternLM2-20B** | [🤗internlm2-20b](https://huggingface.co/internlm/internlm2-20b) | [ internlm2-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b-original) | 2024-01-17 | +| **InternLM2-Chat-20B-SFT** | [🤗internlm2-chat-20b-sft](https://huggingface.co/internlm/internlm2-chat-20b-sft) | [ internlm2-chat-20b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft-original) | 2024-01-17 | +| **InternLM2-Chat-20B** | [🤗internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b) | [ internlm2-chat-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-original) | 2024-01-17 | **Notes:** @@ -85,22 +87,22 @@ The release of InternLM2 series contains two model sizes: 7B and 20B. 7B models ### Objective Evaluation -| Dataset | Baichuan2-7B-Chat | Mistral-7B-Instruct-v0.2 | Qwen-7B-Chat | InternLM2-Chat-7B | ChatGLM3-6B | Baichuan2-13B-Chat | Mixtral-8x7B-Instruct-v0.1 | Qwen-14B-Chat | InternLM2-Chat-20B | -|-----------------------|-------------------|--------------------------|--------------|-------------------|-------------|---------------------|--------------------------------|---------------|---------------------| -| MMLU | 50.1 | 59.2 | 57.1 | 63.7 | 58.0 | 56.6 | 70.3 | 66.7 | 66.5 | -| CMMLU | 53.4 | 42.0 | 57.9 | 63.0 | 57.8 | 54.8 | 50.6 | 68.1 | 65.1 | -| AGIEval | 35.3 | 34.5 | 39.7 | 47.2 | 44.2 | 40.0 | 41.7 | 46.5 | 50.3 | -| C-Eval | 53.9 | 42.4 | 59.8 | 60.8 | 59.1 | 56.3 | 54.0 | 71.5 | 63.0 | -| TrivialQA | 37.6 | 35.0 | 46.1 | 50.8 | 38.1 | 40.3 | 57.7 | 54.5 | 53.9 | -| NaturalQuestions | 12.8 | 8.1 | 18.6 | 24.1 | 14.0 | 12.7 | 22.5 | 22.9 | 25.9 | -| C3 | 78.5 | 66.9 | 84.4 | 91.5 | 79.3 | 84.4 | 82.1 | 91.5 | 93.5 | -| CMRC | 8.1 | 5.6 | 14.6 | 63.8 | 43.2 | 27.8 | 5.3 | 13.0 | 50.4 | -| WinoGrande | 49.9 | 50.8 | 54.2 | 65.8 | 61.7 | 50.9 | 60.9 | 55.7 | 74.8 | -| BBH | 35.9 | 46.5 | 45.5 | 61.2 | 56.0 | 42.5 | 57.3 | 55.8 | 68.3 | -| GSM-8K | 32.4 | 48.3 | 44.1 | 70.7 | 53.8 | 56.0 | 71.7 | 57.7 | 79.6 | -| Math | 5.7 | 8.6 | 12.0 | 23.0 | 20.4 | 4.3 | 22.5 | 27.6 | 31.9 | -| HumanEval | 17.7 | 35.4 | 36.0 | 59.8 | 52.4 | 19.5 | 37.8 | 40.9 | 67.1 | -| MBPP | 37.7 | 25.7 | 33.9 | 51.4 | 55.6 | 40.9 | 40.9 | 30.0 | 65.8 | +| Dataset | Baichuan2-7B-Chat | Mistral-7B-Instruct-v0.2 | Qwen-7B-Chat | InternLM2-Chat-7B | ChatGLM3-6B | Baichuan2-13B-Chat | Mixtral-8x7B-Instruct-v0.1 | Qwen-14B-Chat | InternLM2-Chat-20B | +| ---------------- | ----------------- | ------------------------ | ------------ | ----------------- | ----------- | ------------------ | -------------------------- | ------------- | ------------------ | +| MMLU | 50.1 | 59.2 | 57.1 | 63.7 | 58.0 | 56.6 | 70.3 | 66.7 | 66.5 | +| CMMLU | 53.4 | 42.0 | 57.9 | 63.0 | 57.8 | 54.8 | 50.6 | 68.1 | 65.1 | +| AGIEval | 35.3 | 34.5 | 39.7 | 47.2 | 44.2 | 40.0 | 41.7 | 46.5 | 50.3 | +| C-Eval | 53.9 | 42.4 | 59.8 | 60.8 | 59.1 | 56.3 | 54.0 | 71.5 | 63.0 | +| TrivialQA | 37.6 | 35.0 | 46.1 | 50.8 | 38.1 | 40.3 | 57.7 | 54.5 | 53.9 | +| NaturalQuestions | 12.8 | 8.1 | 18.6 | 24.1 | 14.0 | 12.7 | 22.5 | 22.9 | 25.9 | +| C3 | 78.5 | 66.9 | 84.4 | 91.5 | 79.3 | 84.4 | 82.1 | 91.5 | 93.5 | +| CMRC | 8.1 | 5.6 | 14.6 | 63.8 | 43.2 | 27.8 | 5.3 | 13.0 | 50.4 | +| WinoGrande | 49.9 | 50.8 | 54.2 | 65.8 | 61.7 | 50.9 | 60.9 | 55.7 | 74.8 | +| BBH | 35.9 | 46.5 | 45.5 | 61.2 | 56.0 | 42.5 | 57.3 | 55.8 | 68.3 | +| GSM-8K | 32.4 | 48.3 | 44.1 | 70.7 | 53.8 | 56.0 | 71.7 | 57.7 | 79.6 | +| Math | 5.7 | 8.6 | 12.0 | 23.0 | 20.4 | 4.3 | 22.5 | 27.6 | 31.9 | +| HumanEval | 17.7 | 35.4 | 36.0 | 59.8 | 52.4 | 19.5 | 37.8 | 40.9 | 67.1 | +| MBPP | 37.7 | 25.7 | 33.9 | 51.4 | 55.6 | 40.9 | 40.9 | 30.0 | 65.8 | - Performance of MBPP is reported with MBPP(Sanitized) @@ -108,16 +110,16 @@ The release of InternLM2 series contains two model sizes: 7B and 20B. 7B models - We have evaluated our model on [AlpacaEval 2.0](https://tatsu-lab.github.io/alpaca_eval/) and InternLM2-Chat-20B surpass Claude 2, GPT-4(0613) and Gemini Pro. -| Model Name | Win Rate | Length | -| ----------------------- | -------- | ------ | -| GPT-4 Turbo | 50.00% | 2049 | -| GPT-4 | 23.58% | 1365 | -| GPT-4 0314 | 22.07% | 1371 | -| Mistral Medium | 21.86% | 1500 | -| XwinLM 70b V0.1 | 21.81% | 1775 | -| InternLM2 Chat 20B | 21.75% | 2373 | +| Model Name | Win Rate | Length | +| ------------------ | -------- | ------ | +| GPT-4 Turbo | 50.00% | 2049 | +| GPT-4 | 23.58% | 1365 | +| GPT-4 0314 | 22.07% | 1371 | +| Mistral Medium | 21.86% | 1500 | +| XwinLM 70b V0.1 | 21.81% | 1775 | +| InternLM2 Chat 20B | 21.75% | 2373 | | Mixtral 8x7B v0.1 | 18.26% | 1465 | -| Claude 2 | 17.19% | 1069 | +| Claude 2 | 17.19% | 1069 | | Gemini Pro | 16.85% | 1315 | | GPT-4 0613 | 15.76% | 1140 | | Claude 2.1 | 15.73% | 1096 | @@ -129,9 +131,11 @@ The release of InternLM2 series contains two model sizes: 7B and 20B. 7B models We briefly show the usages with [Transformers](#import-from-transformers), [ModelScope](#import-from-modelscope), and [Web demos](#dialogue). The chat models adopt [chatml format](./chat/chat_format.md) to support both chat and agent applications. To ensure a better usage effect, please make sure that the installed transformers library version meets the following requirements before performing inference with [Transformers](#import-from-transformers) or [ModelScope](#import-from-modelscope): + ``` transformers >= 4.34 ``` + ### Import from Transformers To load the InternLM2-7B-Chat model using Transformers, use the following code: @@ -143,7 +147,7 @@ tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_re # Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error. model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", device_map="auto", trust_remote_code=True, torch_dtype=torch.float16) # (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes. - # InternLM 7B in 4bit will cost nearly 8GB GPU memory. + # InternLM 7B in 4bit will cost nearly 8GB GPU memory. # pip install -U bitsandbytes # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True) # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True) @@ -167,7 +171,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_re # Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error. model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, torch_dtype=torch.float16) # (Optional) If on low resource devices, you can load model in 4-bit or 8-bit to further save GPU memory via bitsandbytes. - # InternLM 7B in 4bit will cost nearly 8GB GPU memory. + # InternLM 7B in 4bit will cost nearly 8GB GPU memory. # pip install -U bitsandbytes # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True) # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True) diff --git a/README_zh-CN.md b/README_zh-CN.md index 0eb6942..49cf811 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -16,6 +16,7 @@ [![license](./assets//license.svg)](https://github.com/open-mmlab/mmdetection/blob/main/LICENSE) [![evaluation](./assets//compass_support.svg)](https://github.com/internLM/OpenCompass/) + [📘商业授权](#开源许可证) | @@ -43,26 +44,26 @@ InternLM2 系列模型在本仓库正式发布，具有如下特性： ## 更新 -[2024.01.23] 我们发布了 InternLM2-Math-7B 和 InternLM2-Math-20B 以及相关的对话模型。InternLM-Math以较小的尺寸超过了ChatGPT的表现。可以点击[InternLM-Math](https://github.com/InternLM/internlm-math)进行下载，并了解详情。 +\[2024.01.23\] 我们发布了 InternLM2-Math-7B 和 InternLM2-Math-20B 以及相关的对话模型。InternLM-Math以较小的尺寸超过了ChatGPT的表现。可以点击[InternLM-Math](https://github.com/InternLM/internlm-math)进行下载，并了解详情。 -[2024.01.17] 我们发布了 InternLM2-7B 和 InternLM2-20B 以及相关的对话模型，InternLM2 在数理、代码、对话、创作等各方面能力都获得了长足进步，综合性能达到开源模型的领先水平。可以点击[下面的模型库](#model-zoo)进行下载或者[查看模型文档](./model_cards/)来了解更多细节. +\[2024.01.17\] 我们发布了 InternLM2-7B 和 InternLM2-20B 以及相关的对话模型，InternLM2 在数理、代码、对话、创作等各方面能力都获得了长足进步，综合性能达到开源模型的领先水平。可以点击[下面的模型库](#model-zoo)进行下载或者[查看模型文档](./model_cards/)来了解更多细节. -[2023.12.13] 我们更新了 InternLM-7B-Chat 和 InternLM-20B-Chat 模型权重。通过改进微调数据和训练策略，新版对话模型生成的回复质量更高、语言风格更加多元。 +\[2023.12.13\] 我们更新了 InternLM-7B-Chat 和 InternLM-20B-Chat 模型权重。通过改进微调数据和训练策略，新版对话模型生成的回复质量更高、语言风格更加多元。 -[2023.09.20] InternLM-20B 已发布，包括基础版和对话版。 +\[2023.09.20\] InternLM-20B 已发布，包括基础版和对话版。 ## Model Zoo -| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date | -|---------------------------|------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------| -| **InternLM2-Base-7B** | [🤗internlm2-base-7b](https://huggingface.co/internlm/internlm2-base-7b) | [ internlm2-base-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b-original) | 2024-01-17 | -| **InternLM2-7B** | [🤗internlm2-7b](https://huggingface.co/internlm/internlm2-7b) | [ internlm2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b-original) | 2024-01-17 | -| **InternLM2-Chat-7B-SFT** | [🤗internlm2-chat-7b-sft](https://huggingface.co/internlm/internlm2-chat-7b-sft) | [ internlm2-chat-7b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft-original) | 2024-01-17 | -| **InternLM2-Chat-7B** | [🤗internlm2-chat-7b](https://huggingface.co/internlm/internlm2-chat-7b) | [ internlm2-chat-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-original) | 2024-01-17 | -| **InternLM2-Base-20B** | [🤗internlm2-base-20b](https://huggingface.co/internlm/internlm2-base-20b) | [ internlm2-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b-original) | 2024-01-17 | -| **InternLM2-20B** | [🤗internlm2-20b](https://huggingface.co/internlm/internlm2-20b) | [ internlm2-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b-original) | 2024-01-17 | -| **InternLM2-Chat-20B-SFT** | [🤗internlm2-chat-20b-sft](https://huggingface.co/internlm/internlm2-chat-20b-sft) | [ internlm2-chat-20b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft-original) | 2024-01-17 | -| **InternLM2-Chat-20B** | [🤗internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b) | [ internlm2-chat-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-original) | 2024-01-17 | +| Model | Transformers(HF) | ModelScope(HF) | OpenXLab(HF) | OpenXLab(Origin) | Release Date | +| -------------------------- | ------------------------------------------ | ---------------------------------------- | -------------------------------------- | ------------------------------------------ | ------------ | +| **InternLM2-Base-7B** | [🤗internlm2-base-7b](https://huggingface.co/internlm/internlm2-base-7b) | [ internlm2-base-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-7b-original) | 2024-01-17 | +| **InternLM2-7B** | [🤗internlm2-7b](https://huggingface.co/internlm/internlm2-7b) | [ internlm2-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-7b-original) | 2024-01-17 | +| **InternLM2-Chat-7B-SFT** | [🤗internlm2-chat-7b-sft](https://huggingface.co/internlm/internlm2-chat-7b-sft) | [ internlm2-chat-7b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-sft-original) | 2024-01-17 | +| **InternLM2-Chat-7B** | [🤗internlm2-chat-7b](https://huggingface.co/internlm/internlm2-chat-7b) | [ internlm2-chat-7b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-7b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-7b-original) | 2024-01-17 | +| **InternLM2-Base-20B** | [🤗internlm2-base-20b](https://huggingface.co/internlm/internlm2-base-20b) | [ internlm2-base-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-base-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-base-20b-original) | 2024-01-17 | +| **InternLM2-20B** | [🤗internlm2-20b](https://huggingface.co/internlm/internlm2-20b) | [ internlm2-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-20b-original) | 2024-01-17 | +| **InternLM2-Chat-20B-SFT** | [🤗internlm2-chat-20b-sft](https://huggingface.co/internlm/internlm2-chat-20b-sft) | [ internlm2-chat-20b-sft](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b-sft/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-sft-original) | 2024-01-17 | +| **InternLM2-Chat-20B** | [🤗internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b) | [ internlm2-chat-20b](https://modelscope.cn/models/Shanghai_AI_Laboratory/internlm2-chat-20b/summary) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b) | [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/header/openxlab_models.svg)](https://openxlab.org.cn/models/detail/OpenLMLab/internlm2-chat-20b-original) | 2024-01-17 | **模型说明：** @@ -83,22 +84,22 @@ InternLM2 系列模型在本仓库正式发布，具有如下特性： ### 客观评测 -| Dataset | Baichuan2-7B-Chat | Mistral-7B-Instruct-v0.2 | Qwen-7B-Chat | InternLM2-Chat-7B | ChatGLM3-6B | Baichuan2-13B-Chat | Mixtral-8x7B-Instruct-v0.1 | Qwen-14B-Chat | InternLM2-Chat-20B | -|-----------------------|-------------------|--------------------------|--------------|-------------------|-------------|---------------------|--------------------------------|---------------|---------------------| -| MMLU | 50.1 | 59.2 | 57.1 | 63.7 | 58.0 | 56.6 | 70.3 | 66.7 | 66.5 | -| CMMLU | 53.4 | 42.0 | 57.9 | 63.0 | 57.8 | 54.8 | 50.6 | 68.1 | 65.1 | -| AGIEval | 35.3 | 34.5 | 39.7 | 47.2 | 44.2 | 40.0 | 41.7 | 46.5 | 50.3 | -| C-Eval | 53.9 | 42.4 | 59.8 | 60.8 | 59.1 | 56.3 | 54.0 | 71.5 | 63.0 | -| TrivialQA | 37.6 | 35.0 | 46.1 | 50.8 | 38.1 | 40.3 | 57.7 | 54.5 | 53.9 | -| NaturalQuestions | 12.8 | 8.1 | 18.6 | 24.1 | 14.0 | 12.7 | 22.5 | 22.9 | 25.9 | -| C3 | 78.5 | 66.9 | 84.4 | 91.5 | 79.3 | 84.4 | 82.1 | 91.5 | 93.5 | -| CMRC | 8.1 | 5.6 | 14.6 | 63.8 | 43.2 | 27.8 | 5.3 | 13.0 | 50.4 | -| WinoGrande | 49.9 | 50.8 | 54.2 | 65.8 | 61.7 | 50.9 | 60.9 | 55.7 | 74.8 | -| BBH | 35.9 | 46.5 | 45.5 | 61.2 | 56.0 | 42.5 | 57.3 | 55.8 | 68.3 | -| GSM-8K | 32.4 | 48.3 | 44.1 | 70.7 | 53.8 | 56.0 | 71.7 | 57.7 | 79.6 | -| Math | 5.7 | 8.6 | 12.0 | 23.0 | 20.4 | 4.3 | 22.5 | 27.6 | 31.9 | -| HumanEval | 17.7 | 35.4 | 36.0 | 59.8 | 52.4 | 19.5 | 37.8 | 40.9 | 67.1 | -| MBPP | 37.7 | 25.7 | 33.9 | 51.4 | 55.6 | 40.9 | 40.9 | 30.0 | 65.8 | +| Dataset | Baichuan2-7B-Chat | Mistral-7B-Instruct-v0.2 | Qwen-7B-Chat | InternLM2-Chat-7B | ChatGLM3-6B | Baichuan2-13B-Chat | Mixtral-8x7B-Instruct-v0.1 | Qwen-14B-Chat | InternLM2-Chat-20B | +| ---------------- | ----------------- | ------------------------ | ------------ | ----------------- | ----------- | ------------------ | -------------------------- | ------------- | ------------------ | +| MMLU | 50.1 | 59.2 | 57.1 | 63.7 | 58.0 | 56.6 | 70.3 | 66.7 | 66.5 | +| CMMLU | 53.4 | 42.0 | 57.9 | 63.0 | 57.8 | 54.8 | 50.6 | 68.1 | 65.1 | +| AGIEval | 35.3 | 34.5 | 39.7 | 47.2 | 44.2 | 40.0 | 41.7 | 46.5 | 50.3 | +| C-Eval | 53.9 | 42.4 | 59.8 | 60.8 | 59.1 | 56.3 | 54.0 | 71.5 | 63.0 | +| TrivialQA | 37.6 | 35.0 | 46.1 | 50.8 | 38.1 | 40.3 | 57.7 | 54.5 | 53.9 | +| NaturalQuestions | 12.8 | 8.1 | 18.6 | 24.1 | 14.0 | 12.7 | 22.5 | 22.9 | 25.9 | +| C3 | 78.5 | 66.9 | 84.4 | 91.5 | 79.3 | 84.4 | 82.1 | 91.5 | 93.5 | +| CMRC | 8.1 | 5.6 | 14.6 | 63.8 | 43.2 | 27.8 | 5.3 | 13.0 | 50.4 | +| WinoGrande | 49.9 | 50.8 | 54.2 | 65.8 | 61.7 | 50.9 | 60.9 | 55.7 | 74.8 | +| BBH | 35.9 | 46.5 | 45.5 | 61.2 | 56.0 | 42.5 | 57.3 | 55.8 | 68.3 | +| GSM-8K | 32.4 | 48.3 | 44.1 | 70.7 | 53.8 | 56.0 | 71.7 | 57.7 | 79.6 | +| Math | 5.7 | 8.6 | 12.0 | 23.0 | 20.4 | 4.3 | 22.5 | 27.6 | 31.9 | +| HumanEval | 17.7 | 35.4 | 36.0 | 59.8 | 52.4 | 19.5 | 37.8 | 40.9 | 67.1 | +| MBPP | 37.7 | 25.7 | 33.9 | 51.4 | 55.6 | 40.9 | 40.9 | 30.0 | 65.8 | - MBPP性能使用的是MBPP(Sanitized)版本数据集 @@ -106,16 +107,16 @@ InternLM2 系列模型在本仓库正式发布，具有如下特性： - 我们评测了InternLM2-Chat在[AlpacaEval 2.0](https://tatsu-lab.github.io/alpaca_eval/) 上的性能，结果表明InternLM2-Chat在AlpacaEval上已经超过了 Claude 2, GPT-4(0613) 和 Gemini Pro. -| Model Name | Win Rate | Length | -| ----------------------- | -------- | ------ | -| GPT-4 Turbo | 50.00% | 2049 | -| GPT-4 | 23.58% | 1365 | -| GPT-4 0314 | 22.07% | 1371 | -| Mistral Medium | 21.86% | 1500 | -| XwinLM 70b V0.1 | 21.81% | 1775 | -| InternLM2 Chat 20B | 21.75% | 2373 | +| Model Name | Win Rate | Length | +| ------------------ | -------- | ------ | +| GPT-4 Turbo | 50.00% | 2049 | +| GPT-4 | 23.58% | 1365 | +| GPT-4 0314 | 22.07% | 1371 | +| Mistral Medium | 21.86% | 1500 | +| XwinLM 70b V0.1 | 21.81% | 1775 | +| InternLM2 Chat 20B | 21.75% | 2373 | | Mixtral 8x7B v0.1 | 18.26% | 1465 | -| Claude 2 | 17.19% | 1069 | +| Claude 2 | 17.19% | 1069 | | Gemini Pro | 16.85% | 1315 | | GPT-4 0613 | 15.76% | 1140 | | Claude 2.1 | 15.73% | 1096 | @@ -127,9 +128,11 @@ InternLM2 系列模型在本仓库正式发布，具有如下特性： 接下来我们展示使用 [Transformers](#import-from-transformers)，[ModelScope](#import-from-modelscope) 和 [Web demo](#dialogue) 进行推理。 对话模型采用了 [chatml 格式](./chat/chat_format.md) 来支持通用对话和智能体应用。 为了保障更好的使用效果，在用 [Transformers](#import-from-transformers) 或 [ModelScope](#import-from-modelscope) 进行推理前，请确保安装的 transformers 库版本满足以下要求： + ``` transformers >= 4.34 ``` + ### 通过 Transformers 加载 通过以下的代码从 Transformers 加载 InternLM2-7B-Chat 模型 （可修改模型名称替换不同的模型） @@ -141,7 +144,7 @@ tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2-chat-7b", trust_re # 设置`torch_dtype=torch.float16`来将模型精度指定为torch.float16，否则可能会因为您的硬件原因造成显存不足的问题。 model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-7b", device_map="auto",trust_remote_code=True, torch_dtype=torch.float16) # (可选) 如果在低资源设备上，可以通过bitsandbytes加载4-bit或8-bit量化的模型，进一步节省GPU显存. - # 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存. + # 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存. # pip install -U bitsandbytes # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True) # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True) @@ -164,7 +167,7 @@ model_dir = snapshot_download('Shanghai_AI_Laboratory/internlm2-chat-7b') tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, torch_dtype=torch.float16) # (可选) 如果在低资源设备上，可以通过bitsandbytes加载4-bit或8-bit量化的模型，进一步节省GPU显存. - # 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存. + # 4-bit 量化的 InternLM 7B 大约会消耗 8GB 显存. # pip install -U bitsandbytes # 8-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_8bit=True) # 4-bit: model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True, load_in_4bit=True) diff --git a/agent/README.md b/agent/README.md index 370415b..693c841 100644 --- a/agent/README.md +++ b/agent/README.md @@ -4,18 +4,18 @@ English | [简体中文](README_zh-CN.md) ## Introduction -InternLM-Chat-7B v1.1 has been released as the first open-source model with code interpreter capabilities, supportting external tools such as Python code interpreter and search engine. +InternLM-Chat-7B v1.1 has been released as the first open-source model with code interpreter capabilities, supporting external tools such as Python code interpreter and search engine. InternLM2-Chat, open sourced on January 17, 2024, further enhances its capabilities in code interpreter and general tool utilization. With improved and more generalized instruction understanding, tool selection, and reflection abilities, InternLM2-Chat can more reliably support complex agents and multi-step tool calling for more intricate tasks. InternLM2-Chat exhibits decent computational and reasoning abilities even without external tools, surpassing ChatGPT in mathematical performance. When combined with a code interpreter, InternLM2-Chat-20B obtains comparable results to GPT-4 on GSM8K and MATH. Leveraging strong foundational capabilities in mathematics and tools, InternLM2-Chat provides practical data analysis capabilities. The results of InternLM2-Chat-20B on math code interpreter is as below: -| | GSM8K | MATH | -| :---: | :---: | :--: | -| InternLM2-Chat-20B | 79.6 | 32.5 | -| InternLM2-Chat-20B with Code Interpreter | 84.5 | 51.2 | -| ChatGPT (GPT-3.5) | 78.2 | 28.0 | -| GPT-4 | 91.4 | 45.8 | +| | GSM8K | MATH | +| :--------------------------------------: | :---: | :--: | +| InternLM2-Chat-20B | 79.6 | 32.5 | +| InternLM2-Chat-20B with Code Interpreter | 84.5 | 51.2 | +| ChatGPT (GPT-3.5) | 78.2 | 28.0 | +| GPT-4 | 91.4 | 45.8 | ## Usages diff --git a/agent/README_zh-CN.md b/agent/README_zh-CN.md index 7f8a240..3b198b1 100644 --- a/agent/README_zh-CN.md +++ b/agent/README_zh-CN.md @@ -10,12 +10,12 @@ InternLM2-Chat 进一步提高了它在代码解释和通用工具调用方面 以下是 InternLM2-Chat-20B 在数学代码解释器上的结果。 -| | GSM8K | MATH | -| :---: | :---: | :--: | -| InternLM2-Chat-20B 单纯依靠内在能力 | 79.6 | 32.5 | -| InternLM2-Chat-20B 配合代码解释器 | 84.5 | 51.2 | -| ChatGPT (GPT-3.5) | 78.2 | 28.0 | -| GPT-4 | 91.4 | 45.8 | +| | GSM8K | MATH | +| :---------------------------------: | :---: | :--: | +| InternLM2-Chat-20B 单纯依靠内在能力 | 79.6 | 32.5 | +| InternLM2-Chat-20B 配合代码解释器 | 84.5 | 51.2 | +| ChatGPT (GPT-3.5) | 78.2 | 28.0 | +| GPT-4 | 91.4 | 45.8 | ## 体验 diff --git a/agent/lagent_zh-CN.md b/agent/lagent_zh-CN.md index 0365969..141a782 100644 --- a/agent/lagent_zh-CN.md +++ b/agent/lagent_zh-CN.md @@ -40,7 +40,7 @@ streamlit run examples/react_web_demo.py ## 用 InternLM-Chat 构建一个 ReAct 智能体 -**注意：**如果你想要启动一个 HuggingFace 的模型，请先运行 pip install -e .[all]。 +\*\*注意：\*\*如果你想要启动一个 HuggingFace 的模型，请先运行 pip install -e .\[all\]。 ```python # Import necessary modules and classes from the "lagent" library. diff --git a/agent/pal_inference.md b/agent/pal_inference.md index c2f874c..82f7aaf 100644 --- a/agent/pal_inference.md +++ b/agent/pal_inference.md @@ -21,20 +21,21 @@ python pal_inference.py \ ``` Parameter explanation: -| Parameter | Description | -| :--------: | :--------------------: | -| \ | Path to the model used for inference | -| \ | Generated code will be saved in the specified output folder | -| --dataset | Name of the dataset used for code generation (defaults to gsm8k) | -| --max_length | Maximum input token length for the model (defaults to 2048) | -| --top_p | Probability threshold for the sum of candidate tokens (defaults to 0.8) | -| --eoh | User input end identifier (defaults to "") | -| --eoa | Model input end identifier (defaults to "") | -| --eos | System input end identifier (defaults to "") | -| --temperature， -t | Sampling temperature during generation (defaults to 1.0) | -| --time_out