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.

Open source LLM with 32k Context Length

115 pointsby shubham_sabooover 1 year ago

5 comments

alsodumbover 1 year ago
Abacus always seemed to me like a 'we got a lot of VC money with inflated claims now we gotta show we do everything' company. I don't really understand what they do, they seem to offer everything but I don't see anyone talking about using their offerings in the real-world. Ever. The only time I see mentions of the company are when I am targeted with ads or promoted posts of the founder.
评论 #37247667 未加载
weinzierlover 1 year ago
This is just another fine-tuned LLaMA and Llama 2, like there are already some. I doubt that this will give seriously meaningful results for long context inference.<p>32k context length sounds nice of course, and it seems to be common to call the just fine-tuned models like that. I think it is more of a marketing thing and we really should distinguish between the context length of the pre-trained model and the fine-tuned model, with the latter being the default meaning of context length.
评论 #37248264 未加载
supermattover 1 year ago
It seems this is built on LLAMA. Did meta change the license to make it open source now? It still seems to be showing otherwise in the repo.<p>Edit: No mention of it being open source in the linked article. Maybe the title here is just wrong? @dang
评论 #37245941 未加载
评论 #37245933 未加载
评论 #37246892 未加载
vekkerover 1 year ago
It&#x27;s probably too new for anyone to have integrated this into text-generation-webui &#x2F; Gradio? I&#x27;ve been looking for a large context LLM (self-hosted or not) for a project, and as a European I unfortunately don&#x27;t have access to Anthropic&#x27;s Claude API yet.
评论 #37246746 未加载
评论 #37247559 未加载
Havocover 1 year ago
Does anyone know if larger context lengths are inherent worse at other task?<p>i.e. all other things being equal is a 8k model better at math than a 32k model
评论 #37247543 未加载
评论 #37248254 未加载