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.

Ollama v0.1.45

111 pointsby lijunhao11 months ago

12 comments

zora_goron11 months ago
I see a couple comments comparing llama.cpp and Ollama, and I think both have utility for different purposes. Having used both llama.cpp (which is fantastic) and Ollama, a couple things that I find valuable about Ollama out-of-the-box --<p>- Automatically loading&#x2F;unloading models from memory - just running the Ollama server is a relatively small footprint; every time a particular model is called it is loaded into memory, and then unloaded after 5 mins of no further usage. It makes it very convenient to spin up different models for different use-cases without having to worry about memory management or manually shutting down those tools when not in use.<p>- OpenAI API compatibility - I run Ollama on a headless machine that has better hardware and connect via SSH port forwarding from my laptop, and with a 1 line change I can reroute any scripts on my laptop from GPT to Llama-3 (or anything else).<p>Overall, at least for tinkering with multiple local models and building small, personal tools, I&#x27;ve found the utility:maintenance ratio of Ollama to be very positive -- thanks to the team for building something so valuable! :)
评论 #40694410 未加载
评论 #40694686 未加载
okwhateverdude11 months ago
I think this is a neat project, and use it a lot. My only complaint is the lack of grammar support. llama.cpp that they wrap will take a grammar. The dumbest patch to enable this is like two lines. And they seem to be willfully ignoring the (pretty trivial) feature for some reason. I&#x27;d rather not maintain a -but-with-grammars fork, so here we are.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;ollama&#x2F;ollama&#x2F;pull&#x2F;4525#issuecomment-2157586947">https:&#x2F;&#x2F;github.com&#x2F;ollama&#x2F;ollama&#x2F;pull&#x2F;4525#issuecomment-2157...</a>
评论 #40693615 未加载
评论 #40693366 未加载
评论 #40693359 未加载
评论 #40694055 未加载
评论 #40693742 未加载
评论 #40694872 未加载
评论 #40694338 未加载
forgingahead11 months ago
Big kudos to the ollama team, echoing others: It just works. Fiddled with llama.cpp for ages trying to get it to run on my GPU, and ollama was setup and done in literally 3 minutes. The memory management of model loading and unloading is great, and now I can hack around and play with different LLMs from a simple API. Highly recommend that folks try it out, I thought local LLMs would be a pain to setup and use, and ollama made it super easy.
I_am_tiberius11 months ago
Can you train models via Ollama or is it just used to run existing&#x2F;pre-defined models?
评论 #40694235 未加载
评论 #40694268 未加载
behnamoh11 months ago
so basically the llama.cpp wrapper got updated because llama.cpp got updated…
krick11 months ago
Is there some llama3-uncensored or something? I&#x27;m waiting for it to appear on ollama list of models since Llama 3 was released.
rcarmo11 months ago
I hope it fixes the current bugs around environment variable handling and pointing it to a specific model directory…
5ytihijik11 months ago
<a href="https:&#x2F;&#x2F;effect.website&#x2F;" rel="nofollow">https:&#x2F;&#x2F;effect.website&#x2F;</a>
yjftsjthsd-h11 months ago
What, if anything, is the difference between release and pre-release in this context?
评论 #40694253 未加载
DidYaWipe11 months ago
Is what?
v3ss0n11 months ago
Reminder: You don&#x27;t need ollama, running llamacpp is as easy as ollama. Ollama is just a wrapper over llamacpp.
评论 #40693442 未加载
评论 #40694262 未加载
评论 #40693666 未加载
评论 #40694159 未加载
评论 #40694728 未加载
评论 #40768454 未加载
doctorpangloss11 months ago
Why is there so much investment in ecosystems outside of Hugging Face? And why do they keep reinventing PyPi?
评论 #40693389 未加载
评论 #40693495 未加载
评论 #40693522 未加载
评论 #40693717 未加载
评论 #40693818 未加载