[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: LLM Experiments, Part 1: Corrections
From: |
Emanuel Berg |
Subject: |
Re: LLM Experiments, Part 1: Corrections |
Date: |
Tue, 23 Jan 2024 04:00:18 +0100 |
User-agent: |
Gnus/5.13 (Gnus v5.13) |
Andrew Hyatt wrote:
> [...] 1. From using gptel and ellama against the same
> model, I see different style responses, and that
> kind of inconsistency would be good to get a handle on;
> LLMs are difficult enough to figure out re what they're
> doing without this additional variation.
>
> Is this keeping the prompt and temperature constant? There's
> inconsistency, though, even keeping everything constant due to
> the randomness of the LLM. I often get very different
> results, for example, to make the demo I shared, I had to run
> it like 5 times because it would either do things too well (no
> need to demo corrections), or not well enough (for example, it
> wouldn't follow my orders to put everything in one paragraph).
>
> 2. Package LLM has the laudible goal of bridgeing between
> models and front-ends, and this is going to be
> vital. 3. (1,2) above lead to the following question:
> 4. Can we write down a list of common configuration
> vars --- here common across the model axis. Make it
> a union of all such params. [...]
Uhm, pardon me for asking but why are the e-mails looking
like this?
--
underground experts united
https://dataswamp.org/~incal
- LLM Experiments, Part 1: Corrections, Andrew Hyatt, 2024/01/21
- Re: LLM Experiments, Part 1: Corrections, Sergey Kostyaev, 2024/01/22
- Re: LLM Experiments, Part 1: Corrections, Andrew Hyatt, 2024/01/22
- Re: LLM Experiments, Part 1: Corrections, T.V Raman, 2024/01/22
- Re: LLM Experiments, Part 1: Corrections, Andrew Hyatt, 2024/01/22
- Re: LLM Experiments, Part 1: Corrections, T.V Raman, 2024/01/22
- Re: LLM Experiments, Part 1: Corrections,
Emanuel Berg <=
- Re: LLM Experiments, Part 1: Corrections, Andrew Hyatt, 2024/01/22
Re: LLM Experiments, Part 1: Corrections, João Távora, 2024/01/22
Re: LLM Experiments, Part 1: Corrections, Karthik Chikmagalur, 2024/01/23
Re: LLM Experiments, Part 1: Corrections, contact, 2024/01/23
Re: LLM Experiments, Part 1: Corrections, Andrew Hyatt, 2024/01/24