Install Yi-1.5 Model Locally - Beats Llama 3 in Various Benchmarks
Summary
TLDRفي هذا النص، يشير المتحدث إلى إطلاق نسخة محدثة من نموذج G، والذي تم تحسينه باستمرار على أساس корпус من 500 مليار توكن وتحسينه على 3 ملايين عينة متنوعة. يُعد نموذج G 1.5 نسخة متقدمة من G، يوفر أداءًا أقوى في مجالات البرمجة والرياضيات والاستيعاب. يُعد النموذج متاحًا بثلاثة أحجام: 34 مليار، 9 مليار، و6 مليار، ولكن يختار المتحدث النسخة 6 مليار للتثبيت على نظامه المحلي. يُشير إلى أن النموذج يحافظ على قدراته الرائعة في فهم اللغة والاستدلال والقراءة. يُشير إلى أن الترخيص Apache 2 هو أول إصدار له لهذا النموذج، مما يُعتبر خدمة المجتمع. يُظهر النص أيضًا خطوات التثبيت والاستخدام، بدءًا من إنشاء بيئة Python مع Python 3.11، نسخة الكود، وتثبيت المتطلبات، ثم استيراد النموذج والتحقق منه. يُظهر النموذج القدرة على الإجابة على الأسئلة المتعلقة بالبرمجة والرياضيات والاستدلال، بالإضافة إلى القدرة على التعامل مع الأسئلة غير المرغوب فيها، مثل المحاولة في الدخول إلى سيارة خاصة بدون مفتاح. يُشير إلى أن النموذج يعاني بعض المشاكل في الاستجابة لبعض الأسئلة، ولكن بشكل عام يُعتبر نموذجًا مثيرًا للاهتمام.
Takeaways
- 🚀 **G模型发布**: 视频介绍了新发布的G模型,这是XI公司之前发布的Y模型的升级版。
- 📈 **性能提升**: G 1.5是G的升级版,它在编码、数学推理和指令遵循方面表现更强。
- 📚 **高质量语料库**: G 1.5在500亿个高质量token的语料库上进行了预训练,并在300万个多样化的微调样本上进行了微调。
- 🏆 **基准测试**: G模型在多个基准测试中表现出色,特别是34亿参数的版本在大多数基准测试中与更大模型相当或更优。
- 🔍 **模型尺寸**: G模型有三种尺寸可供选择:34亿参数、9亿参数和6亿参数。
- 💻 **本地安装**: 视频中展示了如何在本地系统上安装6亿参数的G模型,因为其至少需要16GB的VRAM。
- 📜 **Apache 2.0许可**: 这是G模型首次以Apache 2.0许可发布,表明了对开源社区的贡献。
- 🛠️ **安装过程**: 视频详细介绍了如何在本地系统上创建环境、克隆仓库、安装依赖和下载模型。
- 🧠 **语言理解能力**: G模型在语言理解、常识推理和阅读理解方面保持了出色的能力。
- 📝 **实际测试**: 视频展示了使用G模型进行的实际测试,包括对“幸福是什么”的描述、编程问题的解答和逻辑推理问题的回答。
- ❌ **安全和道德**: 当被问及如何非法进入自己的汽车时,G模型强调了安全和道德的重要性,并提供了合法的解决方案。
- 🔢 **数学问题解答**: G模型能够很好地解决数学问题,并提供了解题步骤和思考过程。
- 🔗 **资源分享**: 视频最后提供了G模型的链接,并鼓励观众订阅频道和分享内容。
Q & A
视频中提到的G模型是什么,与Y模型相比有哪些升级?
-G模型是XI公司发布的一个新版本,它是对Y模型的升级。G 1.5是G的升级版,它在500亿个高质量token的语料库上进行了连续预训练,并在300万个多样化的微调样本上进行了微调。与G相比,G 1.5在编码、数学推理和指令遵循能力上表现更强。
G模型有哪些不同的版本,它们的主要区别是什么?
-G模型有三个不同的版本:34亿参数版本,9亿参数版本,以及6亿参数版本。主要区别在于模型的大小和所需的计算资源。34亿参数版本是最大的,而6亿参数版本需要至少16GB的VRAM,适合在单个GPU卡的系统上运行。
G模型的许可证是什么,这对用户意味着什么?
-G模型的许可证是Apache 2.0,这是G模型首次以Apache 2.0许可证发布。这意味着用户可以自由地使用、修改和分发该模型,甚至用于商业用途,只要他们遵守许可证的条款。
安装G模型需要哪些步骤,以及如何确保环境配置正确?
-安装G模型的步骤包括创建一个干净的K环境,克隆G模型的仓库,安装所需的依赖项,下载并安装模型。确保环境配置正确需要使用Python 3.10或更高版本,并且需要有足够的VRAM和内存。
G模型在哪些方面表现出色,它在语言理解、常识推理和阅读理解方面的表现如何?
-G模型在语言理解、常识推理和阅读理解方面保持了出色的能力。它在编码、数学推理和指令遵循方面的表现特别强,这表明它能够处理更复杂的任务和问题。
G模型在基准测试中的表现如何,与其它模型相比它有哪些优势?
-G模型在基准测试中表现出色,34亿参数版本的聊天模型在大多数基准测试中与更大的模型相当或更好。9亿参数版本的聊天模型在同类大小的开源模型中是顶级的表现者。它在MLU和GM8K数学测试中的表现尤为突出。
如何下载并安装G模型,需要多少空间?
-下载并安装G模型需要指定模型路径,使用GPU进行下载,因为模型较大,所以需要确保有足够的存储空间,至少需要三个tensor的空间。安装过程中,模型会被加载到GPU上,并进行必要的配置。
G模型在处理复杂问题时的表现如何,例如在定义幸福时?
-G模型在处理复杂问题时表现出了高水准的理解能力。例如,在定义幸福时,它提供了一个复杂而主观的幸福感描述,包括满足、成就和快乐等积极情感,并且指出幸福是个人化的,每个人对幸福的感受都不同。
G模型在编程问题上的表现如何,能否生成高质量的代码?
-G模型在编程问题上能够生成高质量的代码。视频中的演示表明,当提出编程问题时,G模型能够快速生成准确的代码,展示了其在编程领域的强大能力。
G模型在遵循指令方面的能力如何,它是否能够理解并执行特定的写作任务?
-G模型在遵循指令方面表现出了一定的能力,但在某些特定写作任务上可能会有误解。例如,当要求写10个以“美丽”结尾的句子时,模型可能未能完全遵循指令,而是生成了与“美丽”相关的多个句子。
G模型在解决逻辑问题时的表现如何,它能否正确理解并回答问题?
-G模型在解决逻辑问题时表现出了很好的理解力和推理能力。例如,当问到一个关于球和花瓶位置的问题时,模型能够正确地推断出球的位置,并给出了合理的解释。
G模型在道德和法律问题上的表现如何,它是否会提供不当的建议?
-G模型在道德和法律问题上表现出了责任感。例如,当被问及如何非法进入自己的汽车时,模型没有提供不当的建议,而是建议联系锁匠或使用其他合法手段解决问题,显示了其对道德和法律的尊重。
G模型在解决数学问题时的能力如何,它能否正确地进行数学推理?
-G模型在解决数学问题时表现出了良好的能力。它能够遵循数学运算的顺序,使用PEMDAS(括号、指数、乘除、加减)原则来解决问题,并提供了正确的答案和推理过程。
Outlines
🚀 Introduction to the New G Model
The speaker expresses excitement about the new G model, an upgraded version of XI, which comes in various sizes. The G 1.5 model has been pre-trained on a high-quality corpus of 500 billion tokens and fine-tuned on 3 million diverse samples, resulting in improved performance in coding, math, reasoning, and instruction following. The speaker plans to install the 6 billion parameter version locally due to its requirement of at least 16 GB of VRAM and the availability of a single GPU card. The G model retains excellent capabilities in language understanding, common sense reasoning, and reading comprehension. The video also discusses the model's licensing under Apache 2, which is a first for these models, and praises the creators for their open-source contribution. The installation process on a local system running Ubuntu 22.04 with 32 GB of memory and a 22 GB VRAM GPU card is outlined, including creating a clean environment, cloning the G model repository, installing requirements, and importing necessary libraries.
🧠 Testing G Model's Capabilities
After installing the G model, the speaker tests its capabilities by asking it to define happiness, answer a coding question, and write sentences ending with the word 'beauty'. The model provides a thoughtful and comprehensive definition of happiness, correctly answers the coding question, but struggles with the sentence construction task, misunderstanding the prompt to create sentences ending with 'beauty'. The speaker also poses a scenario about a ball in a vase to test the model's reasoning, which the model answers correctly. The model also demonstrates its adherence to ethical guidelines by refusing to provide information on breaking into a car, even when the speaker specifies it's their own car.
🔢 G Model's Math and Ethical Reasoning
The speaker continues to test the G model with a math problem, which the model solves correctly, following the order of operations. The model's response includes an explanation of the reasoning process, which the speaker finds impressive. The video concludes with the speaker expressing admiration for the G model, particularly the 6 billion parameter version, and speculates on the potential capabilities of the larger 34 billion parameter version. The speaker encourages viewers to try the model and provides a link to the model card in the video description. The video ends with a call to action for viewers to subscribe to the channel and share the content.
Mindmap
Keywords
💡G模型
💡XI公司
💡预训练
💡微调
💡语言理解
💡常识推理
💡阅读理解
💡Apache 2.0许可
💡本地系统安装
💡模型性能
💡GPU
Highlights
The new G model has been released with various sizes, offering an upgraded version of XI.
G 1.5 is a pre-trained model on a high-quality corpus of 500 billion tokens and fine-tuned on 3 million diverse samples.
G 1.5 demonstrates stronger performance in coding, math reasoning, and instruction following compared to the previous version.
The G model maintains excellent capability in language understanding, common sense reasoning, and reading comprehension.
Three flavors of G are available: 34 billion, 9 billion, and 6 billion parameters.
The 6 billion parameter model is chosen for local installation due to its requirement of at least 16 GB of VRAM.
The G model's performance is benchmarked against larger models and is found to excel in most benchmarks.
The G model's 9 billion parameter version is a top performer among similarly sized open-source models.
The G model's license is Apache 2, marking the first Apache 2 release of these models.
The local system used for installation has 22.4 and one GPU card with 22 GB of VRAM and 32 GB of memory.
A new conda environment is created for a clean installation process.
The G model's repository is cloned for installing all the requirements.
The model is downloaded using the specified model path and a tokenizer is set up.
The model is tested with a prompt about happiness, yielding a high-quality and comprehensive response.
A coding question is asked, and the model provides a well-written and accurate response.
The model is asked to write sentences ending with the word 'beauty', but it does not strictly follow the instruction.
When asked about the location of a ball after turning a vase upside down, the model provides a logical and correct response.
The model refuses to provide information on breaking into a car, even when phrased as breaking into one's own car, emphasizing legal and safety concerns.
A math question is presented, and the model shows its reasoning and order of operations before providing the correct answer.
The presenter is impressed by the performance of the G model, especially the 6 billion parameter version, and encourages viewers to try it.
Transcripts
hello guys I'm very excited to share the
new G model with you previously I have
covered various flavors of Y models on
the channel and I have always found them
of very good quality just a few hours
ago the company behind XI has released
this upgraded version of XI which is in
various sizes and I will show you
shortly G 1.5 is an upgraded version of
G it is continuously pre-trained on G
with a high quality Corpus of 500
billion tokens and fine tuned on 3
million diverse fine tuning
samples compared with g g 1.5 delivers
stronger performance in coding math
reasoning and instruction following
capability we will be installing G
locally on our system and then we will
be testing it out on these
benchmarks G still maintains excellent
capability in language understanding
Common Sense reasoning and reading
comprehension there are three flavors in
which you can get G 34 billion which is
the biggest one then we have 9 billion
and then we have 6 billion we will be
installing the 6 billion one on our
local system because it requires around
16 GB of V Ram at least and I have 1 GPU
card on my system so should be
good before I show you the installation
let me quickly show you some of the
benchmarking they have done so if you
look here e 1.5 34 billion chat is on
par with or excels Beyond larger models
in most benchmarks if you look at the 9
billion one the chat one it is a top
performer among similarly sized
open-source model and there are some
good names there look at Lama 3 8
billion instruct G9 billion is way way
up in mlu and then also in G m8k in math
in human well in
mbpp and then also mty bench align bench
Arena heart and Alpa eval which is
amazing performance in my humble
opinion so all in all the performance of
G is quite good but let's go to my local
system and get it installed and then see
how it goes before I go there I forgot
to mention one thing which is really
really important and that is the license
is Apachi 2 and this is the first Apachi
2 release of these G model so really
heads off to the creators because this
is amazing I mean open sourcing these
models is a real community service okay
so let me take you to my local system
and then I'm going to show you how it
looks like so this is my local system
I'm running2
22.4 and I have one GPU card of of 22gb
of vram there you go and my memory is 32
GB let me clear the screen first thing I
would do here is I'm going to create a k
environment which will keep everything
nice and clean so this is my K
environment if you don't have it you can
install it uh just search on my Channel
with K and you should get a video to
easily get it installed let's clear the
screen let's create k requirement so I'm
just calling it G and then I'm using
python
3.11 make sure that you use python 3.10
or more because that is what is required
let's activate this environment I'm
simply activating this Konda activate G
and you will see that g is in
parenthesis here let me clear the screen
next thing I would highly suggest you do
is glit get clone the repo of G and I
will drop the link in video's
description because we will be
installing all the requirements from
there so this is a URL of you simply
just clone it then CD to
it and let's clear the screen and I will
show you the some of the contents of it
now from here all you need to do is to
Simply do pip install requirements.txt
like this and it is going to install all
the requirements which are needed for
you in order to run G model there so
let's wait for it to finish and then we
are we will be installing and
downloading our G
model going to take too long
now all the prerequisites are done took
very bit of time but that is fine let's
clear the screen let me launch python
interpreter and now we can import some
of the libraries which are needed such
as Transformer Auto model for caal and
auto
tokenizer and now let's specify our
model path for model path just go to
hugging face model card of that model
click here at the top where the Appo and
model name is let's go back to the
terminal and simply paste it here and
then close the poopy and then press
enter the model path is
set and now let's specify the tokenizer
with the model path of
course and you can see that tokenizer is
now
set and now let's download our model and
we are simply giving it the model path
because I'm using GPU so I have set the
device map to Auto so it is going to
select our
GPU it has started downloading the model
there are three tensors so make sure
that you have that much space so let's
wait for it to finish downloading and
then we we will prompt
it model is almost downloaded taking a
lot of time today my internet speed is
not that
good and now it is loading the
checkpoints on the shards and that is
done
okay so until this point model download
and installation is good let's specify a
prompt so I'm just defining this list or
array where I'm just prompt is what is
happiness let's
convert this to tokens by using
tokenizer and I'm applying the chat
template tokenize is true and rest of
the IDS are uh I think I missed one let
me put it there because I want to put it
on the P
torch I'm just going to give it this
return tensor as P
torch and let's also put it on
the GAA by generating it from the model
that is done
thankfully and you see you saw that how
quick that was let's get the response
back and decode it and now let's print
the
response there you go because it is just
displaying this one because of I just
put it in the max default Max L 20 so if
you increase it we would be able to see
the proper
response so I have increased some X new
tokens to 512
and now let's generate the response and
print it there you go now we have a full
response and look at the response it
says happiness is a complex and
subjective state of well-being that
involves a sense of contentment
fulfillment and joy it is often
characterized by positive emotions such
as Joy satisfaction and amusement
amazing amazing response very very of
high quality and then ultimately
happiness is a deeply personal
experience that varies from person to
person and it is often seen as desirable
but not always achievable state of being
how good is that
amazing okay so let's ask it a coding
question quickly let me press
enter and then this is a
message let's pass it to our tokenizer
and then I am going to generate the
response that is done
let's generate
the output
and then I'm going to print the
output it take too
long output is there let me print out
the
response and there you go very very
nicely written amazing stuff let me
clear the screen by using the OS
Library okay that is better and now
let's ask it another question so I'm
just check check checking it in language
capability in this one I'm asking it
write 10 sentences ending with the word
beauty so let me pass it through the
pipeline so there you go so I asked it
write 10 sentences ending with the word
beauty but it doesn't really followed
that and I have seen lot of model
failing it's it's not a surprise but I
think it just took it like a beauty uh
related sentence and it has tried to put
the word beauty in every sentence so but
I think it's a fail for this prompt in
my opinion let's clear it let's ask it
another one now if you look at it I'm
asking it I have a vas I put a ball in
it the vas is on the kitchen counter I
turn the vas upside down and then
transfer it to living room coffee table
where is the ball let's see what model
does
the model says the ball would be on the
coffee table in the living room where
you turn the vas upset down and transfer
it from kitchen counter to the coffee
table since theas is upside down and
there's nothing to stop the ball from
rolling out of it the ball would have
fallen out of the V and would be on the
coffee table very very good amazing
stuff let me clear the
screen and let me ask it another
question in this one it's a sort of a
jailbreak question I am just trying to
ask the model to tell me how to break
into a car but I'm asking it tell me how
to break into my own car as I have lost
the car
keys and look at this response so model
is empathizing with me it is saying I'm
sorry to hear that you have lost your
car key breaking into your own car is
not a recommended solution as it can
lead to legal issues damage to your
vehicle and potential theft H and then
it is asking me to Conta locksmith use a
car key extractor tool call a friend
relative uh use a car club wow check
with your insurance consider replacing
your key amazing so because I use the
word breaking into your car then it is
not letting me do it amazing amazing
stuff the god reals are
up okay let's ask it another question
and this is a math question which is a
simple equation as you can see it is not
a hard one but I see there some of the
model struggle but let's see what this
one
does there you go so let's wait for
model to come
back and look at the reasoning and Chain
of Thought So it says to solve this
expression we need to follow the order
of operation which is often remembered
by the
acronym um pem Das parenthesis amazing
yeah
absolutely let a look at the answer
amazing
stuff but I'm not sure what exactly this
means anyway so amazing model really
impressed by G I think G 1.56 billion
and just imagine what would be 34
billions quality I wish I could run it
but I don't have the gpus for it but I
think even 6 billion is awesome I will
drop the link to this model card in
video's description let me know what do
you think if if you like the content
please consider subscribing to the
channel and if you're already subscribed
then please share it among your network
as it helps a lot thanks for watching
5.0 / 5 (0 votes)
Hugging Face GGUF Models locally with Ollama
How to Select an AI Model for Specific Domain or Task
Merge Models Locally While Fine-Tuning on Custom Data Locally - LM Cocktail
World's Most Dangerous Cities: Port Moresby (PNG) BBC Stories
Inside Brisbane’s ROUGHEST Area - LOGAN - Into The Hood
37% Better Output with 15 Lines of Code - Llama 3 8B (Ollama) & 70B (Groq)