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.

Beginner's Guide to Llama Models

186 pointsby andrewonalmost 2 years ago

14 comments

jmorganalmost 2 years ago
An easy way to try many of the fine-tuned Llama 2 models is <a href="https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama">https:&#x2F;&#x2F;github.com&#x2F;jmorganca&#x2F;ollama</a>.<p>A maintainer of the project has been collecting a full list here (with different quantization levels), most of which are Llama 2-based: <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;mchiang0610&#x2F;b959e3c189ec1e948e4f6a1f737a1fc5" rel="nofollow noreferrer">https:&#x2F;&#x2F;gist.github.com&#x2F;mchiang0610&#x2F;b959e3c189ec1e948e4f6a1f...</a><p>Since the release of Llama 2 the number of models based on it has been growing significantly.. some popular ones:<p>- codeup (A code generation model - DeepSE)<p>- llama2-uncensored (George Sung)<p>- nous-hermes-llama2 (Nous Research)<p>- wizardlm-uncensored (WizardLM)<p>- stablebeluga (Stability AI)<p>The article also recommends oobabooga&#x27;s text-generation-webui which includes a full web dashboard.
评论 #37098236 未加载
评论 #37098265 未加载
thatguymikealmost 2 years ago
I find the whole site being covered in images of skinny waifu girls... offputting. The guide itself seems fine, if high-level. [This](<a href="https:&#x2F;&#x2F;chat.lmsys.org&#x2F;?leaderboard" rel="nofollow noreferrer">https:&#x2F;&#x2F;chat.lmsys.org&#x2F;?leaderboard</a>) is a really nice link I hadn&#x27;t seen before.
评论 #37097982 未加载
评论 #37097873 未加载
评论 #37097952 未加载
评论 #37098186 未加载
评论 #37097961 未加载
评论 #37098001 未加载
milaralmost 2 years ago
This is literally AI generated txt and gen’d images.<p>HN isn’t prepared yet.<p>Prepare for 100x more of these.
评论 #37098015 未加载
ulnarkresstyalmost 2 years ago
I tried multiple flavors of llama models, they are all quite dumb. Even the 70b parameter one. It knows about more things which the smaller models just hallucinate when asked, but still cannot do even slightly more complex tasks.<p>I&#x27;m also not sure about the current testing methodologies i.e. the &#x27;passed the SAT&#x27; hype. Given that the training set already contains much of the information, we should probably compare the AI results with humans having unlimited time and access to the required material.
评论 #37104741 未加载
cowthulhualmost 2 years ago
Does anyone know how well a fine-tuned Llama model will do compared to GPT 4 on complex tasks?
评论 #37097835 未加载
评论 #37098011 未加载
yu3zhou4almost 2 years ago
Can you recommend another systematized guides like this about LLMs and ML in general? Even though was quite limited in info, I like the structured and concise form and I’d be happy to learn about similar blog posts
评论 #37098100 未加载
marcopicentinialmost 2 years ago
Can I train a llama 2 model on custom data and make it expert on my data knowledge?<p>For example, If I give it thousands of law pages it will be a domain expert about law ?
avion23almost 2 years ago
I&#x27;ve evaluated some models. The best ones are based on llama-2. Good is for example codeup-llama-2-13b-chat-hf<p>Uncensored (partially) is nous-hermes-llama2-13b
tony12345678almost 2 years ago
As a Mac user, I think Ollama is amazing. Thank you! :). Is there any chance that functionality could be added for fine-tuning (e.g. document&#x2F;text file uploads)?
crossroadsguyalmost 2 years ago
What&#x27;s a good and friendly place to start for a seasoned Android developer to get a peek into the world of AI&#x2F;ML as we are seeing all this today (or specifically last few months maybe), who is kind of having a FOMO cum curiosity (and a little worry about career&#x2F;future and all) about all this? To get a taste of things.
jbjbjbjbalmost 2 years ago
I tried running a llama model using oobabooga but kept running into one problem after the next.<p>Anyone know of a config that might work (even quite slowly) on an i9 laptop, 32gb ram with nvidia graphics 8gb?
MahdeenSkyalmost 2 years ago
+1 uncensored models
neilvalmost 2 years ago
&gt; <i>How to install Llama models?</i><p>&gt; <i>See the installation guide for Windows and the installation guide for Mac.</i><p>Much &quot;open&quot; LLM&#x2F;SD&#x2F;etc. grassroots stuff seems to be shooting themselves in the face, by pushing others to closed platforms.<p>Now is one of the times to be increasing pressure for open platforms, not backsliding.
评论 #37097978 未加载
speedgoosealmost 2 years ago
What are the hardware requirements to fine tune llama ?
评论 #37098618 未加载