TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Getting Started with Mistral-7b-Instruct-v0.1

140 pointsby 3Sophonsover 1 year ago

11 comments

udev4096over 1 year ago
How is this different than ollama (<a href="https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama">https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama</a>)? I would argue it&#x27;s even simpler to run LLMs locally with ollama
评论 #38361339 未加载
politelemonover 1 year ago
Mistral have created a docker image which hosts their model in vllm. Vllm creates an openai like http API interface.<p><a href="https:&#x2F;&#x2F;docs.mistral.ai&#x2F;quickstart&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;docs.mistral.ai&#x2F;quickstart&#x2F;</a>
评论 #38360381 未加载
评论 #38360257 未加载
jestersonover 1 year ago
Does anyone have any feedback on using those open-source models with any language except English? Particularly non-western group of languages like korean&#x2F;japanese&#x2F;chinese?<p>Will assess myself but wonder if anyone tried.
评论 #38360419 未加载
评论 #38361486 未加载
评论 #38361394 未加载
评论 #38361130 未加载
评论 #38360528 未加载
MaKeyover 1 year ago
What are Mistrals strengths and weaknesses? I tried it for infrastructure as code and it wasn&#x27;t able to output more than the most basic examples, let alone modify them.
评论 #38362370 未加载
评论 #38366153 未加载
评论 #38363939 未加载
评论 #38362250 未加载
xeckrover 1 year ago
Thanks for sharing this!<p>I read somewhere that Mistral 7B had a similar performance to GPT-3, but it seems to be miles behind it unfortunately.
评论 #38361825 未加载
评论 #38360635 未加载
iAkashPaulover 1 year ago
llama.cpp can run the Q4 variant of the same at 30tok&#x2F;s on an M1 Pro unlike the 20tok&#x2F;s being quoted
评论 #38364254 未加载
xrdover 1 year ago
I really like the post that they mention (<a href="https:&#x2F;&#x2F;www.secondstate.io&#x2F;articles&#x2F;fast-llm-inference&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.secondstate.io&#x2F;articles&#x2F;fast-llm-inference&#x2F;</a>). The reasons for avoiding python all resonate with me. I&#x27;m excited to play with WASI-NN (<a href="https:&#x2F;&#x2F;github.com&#x2F;WebAssembly&#x2F;wasi-nn">https:&#x2F;&#x2F;github.com&#x2F;WebAssembly&#x2F;wasi-nn</a>) and that rust code is very readable to load up a GGUL model.
评论 #38364881 未加载
smcleodover 1 year ago
It seems a lot slower than ollama &#x2F; LM Studio. Is that likely because it’s not optimised as much or a limitation of some sort?
android521over 1 year ago
The demo looks too slow for practical usage. How much it will cost if i host it in cloud to get instant response similar to the speed of openAI?
评论 #38373931 未加载
评论 #38361897 未加载
tyayersover 1 year ago
Impressive use of wasmedge, great to see ML projects getting away from python for efficiency&#x27;s sake, thanks for sharing!
tormehover 1 year ago
The WasmEdge README gives me the heebie-jeebies. Starry-eyed emojis, highlights use-case for today&#x27;s most trendy thing even though it&#x27;s general-purpose, mentions blockchain. This reeks of former cryptobros chasing the next big thing. I&#x27;d trust Wasmtime more.
评论 #38365221 未加载