InternLM
๐ join us on Discord and WeChat
Introduction
InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios. The model has the following characteristics:
Outstanding reasoning capability: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-9B.
1M Context window: Nearly perfect at finding needles in the haystack with 1M-long context, with leading performance on long-context tasks like LongBench. Try it with LMDeploy for 1M-context inference.
Stronger tool use: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation has be released in MindSearch. InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See examples.
InternLM2.5-7B-Chat
Performance Evaluation
We conducted a comprehensive evaluation of InternLM using the open-source evaluation tool OpenCompass. The evaluation covered five dimensions of capabilities: disciplinary competence, language competence, knowledge competence, inference competence, and comprehension competence. Here are some of the evaluation results, and you can visit the OpenCompass leaderboard for more evaluation results.
Benchmark | InternLM2.5-7B-Chat | Llama3-8B-Instruct | Gemma2-9B-IT | Yi-1.5-9B-Chat | GLM-4-9B-Chat | Qwen2-7B-Instruct |
---|---|---|---|---|---|---|
MMLU (5-shot) | 72.8 | 68.4 | 70.9 | 71.0 | 71.4 | 70.8 |
CMMLU (5-shot) | 78.0 | 53.3 | 60.3 | 74.5 | 74.5 | 80.9 |
BBH (3-shot CoT) | 71.6 | 54.4 | 68.2* | 69.6 | 69.6 | 65.0 |
MATH (0-shot CoT) | 60.1 | 27.9 | 46.9 | 51.1 | 51.1 | 48.6 |
GSM8K (0-shot CoT) | 86.0 | 72.9 | 88.9 | 80.1 | 85.3 | 82.9 |
GPQA (0-shot) | 38.4 | 26.1 | 33.8 | 37.9 | 36.9 | 38.4 |
- The evaluation results were obtained from OpenCompass (some data marked with *, which means come from the original papers), and evaluation configuration can be found in the configuration files provided by OpenCompass.
- The evaluation data may have numerical differences due to the version iteration of OpenCompass, so please refer to the latest evaluation results of OpenCompass.
Limitations: Although we have made efforts to ensure the safety of the model during the training process and to encourage the model to generate text that complies with ethical and legal requirements, the model may still produce unexpected outputs due to its size and probabilistic generation paradigm. For example, the generated responses may contain biases, discrimination, or other harmful content. Please do not propagate such content. We are not responsible for any consequences resulting from the dissemination of harmful information.
Import from Transformers
To load the InternLM2.5 7B Chat model using Transformers, use the following code:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2_5-7b-chat", trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and cause OOM Error.
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2_5-7b-chat", torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()
response, history = model.chat(tokenizer, "hello", history=[])
print(response)
# Hello! How can I help you today?
response, history = model.chat(tokenizer, "please provide three suggestions about time management", history=history)
print(response)
The responses can be streamed using stream_chat
:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "internlm/internlm2_5-7b-chat"
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.float16, trust_remote_code=True).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = model.eval()
length = 0
for response, history in model.stream_chat(tokenizer, "Hello", history=[]):
print(response[length:], flush=True, end="")
length = len(response)
Deployment
llama.cpp
internlm/internlm2_5-7b-chat-gguf offers internlm2_5-7b-chat
models in GGUF format in both half precision and various low-bit quantized versions, including q5_0
, q5_k_m
, q6_k
, and q8_0
.
LMDeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.
pip install lmdeploy
You can run batch inference locally with the following python code:
import lmdeploy
pipe = lmdeploy.pipeline("internlm/internlm2_5-7b-chat")
response = pipe(["Hi, pls intro yourself", "Shanghai is"])
print(response)
Or you can launch an OpenAI compatible server with the following command:
lmdeploy serve api_server internlm/internlm2_5-7b-chat --model-name internlm2_5-7b-chat --server-port 23333
Then you can send a chat request to the server:
curl http://localhost:23333/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "internlm2_5-7b-chat",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Introduce deep learning to me."}
]
}'
Find more details in the LMDeploy documentation
vLLM
Launch OpenAI compatible server with vLLM>=0.3.2
:
pip install vllm
python -m vllm.entrypoints.openai.api_server --model internlm/internlm2_5-7b-chat --served-model-name internlm2_5-7b-chat --trust-remote-code
Then you can send a chat request to the server:
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "internlm2_5-7b-chat",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Introduce deep learning to me."}
]
}'
Find more details in the vLLM documentation
Open Source License
The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please fill in the application form (English)/็ณ่ฏท่กจ๏ผไธญๆ๏ผ. For other questions or collaborations, please contact internlm@pjlab.org.cn.
Citation
@misc{cai2024internlm2,
title={InternLM2 Technical Report},
author={Zheng Cai and Maosong Cao and Haojiong Chen and Kai Chen and Keyu Chen and Xin Chen and Xun Chen and Zehui Chen and Zhi Chen and Pei Chu and Xiaoyi Dong and Haodong Duan and Qi Fan and Zhaoye Fei and Yang Gao and Jiaye Ge and Chenya Gu and Yuzhe Gu and Tao Gui and Aijia Guo and Qipeng Guo and Conghui He and Yingfan Hu and Ting Huang and Tao Jiang and Penglong Jiao and Zhenjiang Jin and Zhikai Lei and Jiaxing Li and Jingwen Li and Linyang Li and Shuaibin Li and Wei Li and Yining Li and Hongwei Liu and Jiangning Liu and Jiawei Hong and Kaiwen Liu and Kuikun Liu and Xiaoran Liu and Chengqi Lv and Haijun Lv and Kai Lv and Li Ma and Runyuan Ma and Zerun Ma and Wenchang Ning and Linke Ouyang and Jiantao Qiu and Yuan Qu and Fukai Shang and Yunfan Shao and Demin Song and Zifan Song and Zhihao Sui and Peng Sun and Yu Sun and Huanze Tang and Bin Wang and Guoteng Wang and Jiaqi Wang and Jiayu Wang and Rui Wang and Yudong Wang and Ziyi Wang and Xingjian Wei and Qizhen Weng and Fan Wu and Yingtong Xiong and Chao Xu and Ruiliang Xu and Hang Yan and Yirong Yan and Xiaogui Yang and Haochen Ye and Huaiyuan Ying and Jia Yu and Jing Yu and Yuhang Zang and Chuyu Zhang and Li Zhang and Pan Zhang and Peng Zhang and Ruijie Zhang and Shuo Zhang and Songyang Zhang and Wenjian Zhang and Wenwei Zhang and Xingcheng Zhang and Xinyue Zhang and Hui Zhao and Qian Zhao and Xiaomeng Zhao and Fengzhe Zhou and Zaida Zhou and Jingming Zhuo and Yicheng Zou and Xipeng Qiu and Yu Qiao and Dahua Lin},
year={2024},
eprint={2403.17297},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
็ฎไป
InternLM2.5 ๏ผๅณไนฆ็ยทๆตฆ่ฏญๅคงๆจกๅ็ฌฌ 2.5 ไปฃ๏ผๅผๆบไบ้ขๅๅฎ็จๅบๆฏ็70ไบฟๅๆฐๅบ็กๆจกๅไธๅฏน่ฏๆจกๅ ๏ผInternLM2.5-7B-Chat๏ผใๆจกๅๅ ทๆไปฅไธ็น็น๏ผ
- ๅ่ถ็ๆจ็ๆง่ฝ๏ผๅจๆฐๅญฆๆจ็ๆน้ขๅๅพไบๅ้็บงๆจกๅๆไผ็ฒพๅบฆ๏ผ่ถ ่ถไบ Llama3 ๅ Gemma2-9Bใ
- ๆๆๆฏๆ็พไธๅญ่ถ ้ฟไธไธๆ๏ผๆจกๅๅจ 1 ็พไธๅญ้ฟ่พๅ ฅไธญๅ ไนๅฎ็พๅฐๅฎ็ฐ้ฟๆโๅคงๆตทๆ้โ๏ผ่ไธๅจ LongBench ็ญ้ฟๆไปปๅกไธญ็่กจ็ฐไน่พพๅฐๅผๆบๆจกๅไธญ็้ขๅ ๆฐดๅนณใ ๅฏไปฅ้่ฟ LMDeploy ๅฐ่ฏ็พไธๅญ่ถ ้ฟไธไธๆๆจ็ใ
- ๅทฅๅ ท่ฐ็จ่ฝๅๆดไฝๅ็บง๏ผInternLM2.5 ๆฏๆไปไธ็พไธช็ฝ้กตๆ้ๆๆไฟกๆฏ่ฟ่กๅๆๆจ็๏ผ็ธๅ ณๅฎ็ฐๅทฒๅผๆบๅฐ MindSearchใInternLM2.5 ๅ ทๆๆดๅผบๅๆดๅ ทๆๆณๅๆง็ๆไปค็่งฃใๅทฅๅ ท็ญ้ไธ็ปๆๅๆ็ญ่ฝๅ๏ผๆฐ็ๆจกๅๅฏไปฅๆดๅฏ้ ๅฐๆฏๆๅคๆๆบ่ฝไฝ็ๆญๅปบ๏ผๆฏๆๅฏนๅทฅๅ ท่ฟ่กๆๆ็ๅค่ฝฎ่ฐ็จ๏ผๅฎๆ่พๅคๆ็ไปปๅกใๅฏไปฅๆฅ็ๆดๅคๆ ทไพใ
InternLM2.5-7B-Chat
ๆง่ฝ่ฏๆต
ๆไปฌไฝฟ็จๅผๆบ่ฏๆตๅทฅๅ ท OpenCompass ไปๅญฆ็ง็ปผๅ่ฝๅใ่ฏญ่จ่ฝๅใ็ฅ่ฏ่ฝๅใๆจ็่ฝๅใ็่งฃ่ฝๅไบๅคง่ฝๅ็ปดๅบฆๅฏนInternLMๅผๅฑๅ จ้ข่ฏๆต๏ผ้จๅ่ฏๆต็ปๆๅฆไธ่กจๆ็คบ๏ผๆฌข่ฟ่ฎฟ้ฎ OpenCompass ๆฆๅ ่ทๅๆดๅค็่ฏๆต็ปๆใ
่ฏๆต้\ๆจกๅ | InternLM2.5-7B-Chat | Llama3-8B-Instruct | Gemma2-9B-IT | Yi-1.5-9B-Chat | GLM-4-9B-Chat | Qwen2-7B-Instruct |
---|---|---|---|---|---|---|
MMLU (5-shot) | 72.8 | 68.4 | 70.9 | 71.0 | 71.4 | 70.8 |
CMMLU (5-shot) | 78.0 | 53.3 | 60.3 | 74.5 | 74.5 | 80.9 |
BBH (3-shot CoT) | 71.6 | 54.4 | 68.2* | 69.6 | 69.6 | 65.0 |
MATH (0-shot CoT) | 60.1 | 27.9 | 46.9 | 51.1 | 51.1 | 48.6 |
GSM8K (0-shot CoT) | 86.0 | 72.9 | 88.9 | 80.1 | 85.3 | 82.9 |
GPQA (0-shot) | 38.4 | 26.1 | 33.8 | 37.9 | 36.9 | 38.4 |
- ไปฅไธ่ฏๆต็ปๆๅบไบ OpenCompass ่ทๅพ๏ผ้จๅๆฐๆฎๆ ๆณจ
*
ไปฃ่กจๆฐๆฎๆฅ่ชๅๅง่ฎบๆ๏ผ๏ผๅ ทไฝๆต่ฏ็ป่ๅฏๅ่ง OpenCompass ไธญๆไพ็้ ็ฝฎๆไปถใ - ่ฏๆตๆฐๆฎไผๅ OpenCompass ็็ๆฌ่ฟญไปฃ่ๅญๅจๆฐๅผๅทฎๅผ๏ผ่ฏทไปฅ OpenCompass ๆๆฐ็็่ฏๆต็ปๆไธบไธปใ
ๅฑ้ๆง๏ผ ๅฐฝ็ฎกๅจ่ฎญ็ป่ฟ็จไธญๆไปฌ้ๅธธๆณจ้ๆจกๅ็ๅฎๅ จๆง๏ผๅฐฝๅไฟไฝฟๆจกๅ่พๅบ็ฌฆๅไผฆ็ๅๆณๅพ่ฆๆฑ็ๆๆฌ๏ผไฝๅ้ไบๆจกๅๅคงๅฐไปฅๅๆฆ็็ๆ่ๅผ๏ผๆจกๅๅฏ่ฝไผไบง็ๅ็งไธ็ฌฆๅ้ขๆ็่พๅบ๏ผไพๅฆๅๅคๅ ๅฎนๅ ๅซๅ่งใๆญง่ง็ญๆๅฎณๅ ๅฎน๏ผ่ฏทๅฟไผ ๆญ่ฟไบๅ ๅฎนใ็ฑไบไผ ๆญไธ่ฏไฟกๆฏๅฏผ่ด็ไปปไฝๅๆ๏ผๆฌ้กน็ฎไธๆฟๆ ่ดฃไปปใ
้่ฟ Transformers ๅ ่ฝฝ
้่ฟไปฅไธ็ไปฃ็ ๅ ่ฝฝ InternLM2.5 7B Chat ๆจกๅ
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm2_5-7b-chat", trust_remote_code=True)
# `torch_dtype=torch.float16` ๅฏไปฅไปคๆจกๅไปฅ float16 ็ฒพๅบฆๅ ่ฝฝ๏ผๅฆๅ transformers ไผๅฐๆจกๅๅ ่ฝฝไธบ float32๏ผๅฏผ่ดๆพๅญไธ่ถณ
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2_5-7b-chat", torch_dtype=torch.float16, trust_remote_code=True).cuda()
model = model.eval()
response, history = model.chat(tokenizer, "ไฝ ๅฅฝ", history=[])
print(response)
# ไฝ ๅฅฝ๏ผๆไปไนๆๅฏไปฅๅธฎๅฉไฝ ็ๅ๏ผ
response, history = model.chat(tokenizer, "่ฏทๆไพไธไธช็ฎก็ๆถ้ด็ๅปบ่ฎฎใ", history=history)
print(response)
ๅฆๆๆณ่ฟ่กๆตๅผ็ๆ๏ผๅๅฏไปฅไฝฟ็จ stream_chat
ๆฅๅฃ๏ผ
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "internlm/internlm2_5-7b-chat"
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dype=torch.float16, trust_remote_code=True).cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = model.eval()
length = 0
for response, history in model.stream_chat(tokenizer, "ไฝ ๅฅฝ", history=[]):
print(response[length:], flush=True, end="")
length = len(response)
้จ็ฝฒ
LMDeploy
LMDeploy ็ฑ MMDeploy ๅ MMRazor ๅข้่ๅๅผๅ๏ผๆฏๆถต็ไบ LLM ไปปๅก็ๅ จๅฅ่ฝป้ๅใ้จ็ฝฒๅๆๅก่งฃๅณๆนๆกใ
pip install lmdeploy
ไฝ ๅฏไปฅไฝฟ็จไปฅไธ python ไปฃ็ ่ฟ่กๆฌๅฐๆน้ๆจ็:
import lmdeploy
pipe = lmdeploy.pipeline("internlm/internlm2_5-7b-chat")
response = pipe(["Hi, pls intro yourself", "Shanghai is"])
print(response)
ๆ่ ไฝ ๅฏไปฅไฝฟ็จไปฅไธๅฝไปคๅฏๅจๅ ผๅฎน OpenAI API ็ๆๅก:
lmdeploy serve api_server internlm/internlm2_5-7b-chat --model-name internlm2_5-7b-chat --server-port 23333
็ถๅไฝ ๅฏไปฅๅๆๅก็ซฏๅ่ตทไธไธช่ๅคฉ่ฏทๆฑ:
curl http://localhost:23333/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "internlm2_5-7b-chat",
"messages": [
{"role": "system", "content": "ไฝ ๆฏไธชๅๅ็AIๅฉๆใ"},
{"role": "user", "content": "ไป็ปไธไธๆทฑๅบฆๅญฆไน ใ"}
]
}'
ๆดๅคไฟกๆฏ่ฏทๆฅ็ LMDeploy ๆๆกฃ
vLLM
ไฝฟ็จvLLM>=0.3.2
ๅฏๅจๅ
ผๅฎน OpenAI API ็ๆๅก:
pip install vllm
python -m vllm.entrypoints.openai.api_server --model internlm/internlm2_5-7b-chat --served-model-name internlm2_5-7b-chat --trust-remote-code
็ถๅไฝ ๅฏไปฅๅๆๅก็ซฏๅ่ตทไธไธช่ๅคฉ่ฏทๆฑ:
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "internlm2_5-7b-chat",
"messages": [
{"role": "system", "content": "ไฝ ๆฏไธชๅๅ็AIๅฉๆใ"},
{"role": "user", "content": "ไป็ปไธไธๆทฑๅบฆๅญฆไน ใ"}
]
}'
ๆดๅคไฟกๆฏ่ฏทๆฅ็ vLLM ๆๆกฃ
ๅผๆบ่ฎธๅฏ่ฏ
ๆฌไปๅบ็ไปฃ็ ไพ็ ง Apache-2.0 ๅ่ฎฎๅผๆบใๆจกๅๆ้ๅฏนๅญฆๆฏ็ ็ฉถๅฎๅ จๅผๆพ๏ผไนๅฏ็ณ่ฏทๅ ่ดน็ๅไธไฝฟ็จๆๆ๏ผ็ณ่ฏท่กจ๏ผใๅ ถไป้ฎ้ขไธๅไฝ่ฏท่็ณป internlm@pjlab.org.cnใ
ๅผ็จ
@misc{cai2024internlm2,
title={InternLM2 Technical Report},
author={Zheng Cai and Maosong Cao and Haojiong Chen and Kai Chen and Keyu Chen and Xin Chen and Xun Chen and Zehui Chen and Zhi Chen and Pei Chu and Xiaoyi Dong and Haodong Duan and Qi Fan and Zhaoye Fei and Yang Gao and Jiaye Ge and Chenya Gu and Yuzhe Gu and Tao Gui and Aijia Guo and Qipeng Guo and Conghui He and Yingfan Hu and Ting Huang and Tao Jiang and Penglong Jiao and Zhenjiang Jin and Zhikai Lei and Jiaxing Li and Jingwen Li and Linyang Li and Shuaibin Li and Wei Li and Yining Li and Hongwei Liu and Jiangning Liu and Jiawei Hong and Kaiwen Liu and Kuikun Liu and Xiaoran Liu and Chengqi Lv and Haijun Lv and Kai Lv and Li Ma and Runyuan Ma and Zerun Ma and Wenchang Ning and Linke Ouyang and Jiantao Qiu and Yuan Qu and Fukai Shang and Yunfan Shao and Demin Song and Zifan Song and Zhihao Sui and Peng Sun and Yu Sun and Huanze Tang and Bin Wang and Guoteng Wang and Jiaqi Wang and Jiayu Wang and Rui Wang and Yudong Wang and Ziyi Wang and Xingjian Wei and Qizhen Weng and Fan Wu and Yingtong Xiong and Chao Xu and Ruiliang Xu and Hang Yan and Yirong Yan and Xiaogui Yang and Haochen Ye and Huaiyuan Ying and Jia Yu and Jing Yu and Yuhang Zang and Chuyu Zhang and Li Zhang and Pan Zhang and Peng Zhang and Ruijie Zhang and Shuo Zhang and Songyang Zhang and Wenjian Zhang and Wenwei Zhang and Xingcheng Zhang and Xinyue Zhang and Hui Zhao and Qian Zhao and Xiaomeng Zhao and Fengzhe Zhou and Zaida Zhou and Jingming Zhuo and Yicheng Zou and Xipeng Qiu and Yu Qiao and Dahua Lin},
year={2024},
eprint={2403.17297},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 42,856