from Hacker News

Beginner's Guide to Llama Models

by andrewon on 8/12/23, 5:40 AM with 40 comments

• by jmorgan on 8/12/23, 7:56 AM

  An easy way to try many of the fine-tuned Llama 2 models is https://github.com/jmorganca/ollama.

  A maintainer of the project has been collecting a full list here (with different quantization levels), most of which are Llama 2-based: https://gist.github.com/mchiang0610/b959e3c189ec1e948e4f6a1f...

  Since the release of Llama 2 the number of models based on it has been growing significantly.. some popular ones:

  - codeup (A code generation model - DeepSE)

  - llama2-uncensored (George Sung)

  - nous-hermes-llama2 (Nous Research)

  - wizardlm-uncensored (WizardLM)

  - stablebeluga (Stability AI)

  The article also recommends oobabooga's text-generation-webui which includes a full web dashboard.

• by thatguymike on 8/12/23, 6:55 AM

  I find the whole site being covered in images of skinny waifu girls... offputting. The guide itself seems fine, if high-level. [This](https://chat.lmsys.org/?leaderboard) is a really nice link I hadn't seen before.

• by milar on 8/12/23, 7:46 AM

  This is literally AI generated txt and gen’d images.

  HN isn’t prepared yet.

  Prepare for 100x more of these.

• by ulnarkressty on 8/12/23, 8:00 AM

  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.

  I'm also not sure about the current testing methodologies i.e. the 'passed the SAT' 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.

• by cowthulhu on 8/12/23, 6:33 AM

  Does anyone know how well a fine-tuned Llama model will do compared to GPT 4 on complex tasks?

• by yu3zhou4 on 8/12/23, 7:47 AM

  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

• by marcopicentini on 8/12/23, 8:47 AM

  Can I train a llama 2 model on custom data and make it expert on my data knowledge?

  For example, If I give it thousands of law pages it will be a domain expert about law ?

• by avion23 on 8/12/23, 8:27 AM

  I've evaluated some models. The best ones are based on llama-2. Good is for example codeup-llama-2-13b-chat-hf

  Uncensored (partially) is nous-hermes-llama2-13b

• by tony12345678 on 8/17/23, 9:16 PM

  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/text file uploads)?

• by crossroadsguy on 8/12/23, 9:27 AM

  What's a good and friendly place to start for a seasoned Android developer to get a peek into the world of AI/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/future and all) about all this? To get a taste of things.

• by jbjbjbjb on 8/12/23, 8:48 AM

  I tried running a llama model using oobabooga but kept running into one problem after the next.

  Anyone know of a config that might work (even quite slowly) on an i9 laptop, 32gb ram with nvidia graphics 8gb?

• by MahdeenSky on 8/12/23, 7:02 AM

  +1 uncensored models

• by neilv on 8/12/23, 7:36 AM

  > How to install Llama models?

  > See the installation guide for Windows and the installation guide for Mac.

  Much "open" LLM/SD/etc. grassroots stuff seems to be shooting themselves in the face, by pushing others to closed platforms.

  Now is one of the times to be increasing pressure for open platforms, not backsliding.

• by speedgoose on 8/12/23, 6:24 AM

  What are the hardware requirements to fine tune llama ?