Questions tagged [text-generation]
The text-generation tag has no usage guidance.
14
questions
-1
votes
0
answers
10
views
Requesting Help with Article Generator Project
So, I have been working on a photo/video sharing platform for some time. It’s a place where people can host events, and guests can upload pictures and videos they take during the event. We also have ...
- 1
4
votes
2
answers
464
views
Is the text of a LLM determined by a random seed?
Is the generation of text in a LLM determined by a random seed, just like procedurally generated worlds in video games?
user4618
0
votes
1
answer
32
views
Can batching help increase offline text-generation performance significantly?
I have a collection of documents, each <1k tokens. I want to evaluate each of them with a given prompt. My prompt is 330 tokens.
I have a Quadro RTX8000, which has 48Gb of memory, and 672Gb/s ...
- 101
0
votes
0
answers
30
views
Fast Mistral text generation
I would like to ask the general public about how fast they can get Mistral text generation going on basic hardware. Consider 2 mid-tier GPUs, 60 Gig ram and amnd 20 cores. How quickly can you get ...
- 119
1
vote
2
answers
107
views
prompt llm to generate an email with well structured line breaks
I'm using the latest llms (mixtral/gemini/..)
I'm generating emails and I'm satisfied with the results except that the sentences are without proper line breaks.
The greeting and signature parts are ok ...
- 131
1
vote
1
answer
76
views
Why does RAG work?
Consider a corpus of answer sheets of History exam at high school level. Say it is 10 GiB in size.
Case 1
Assume that these answer sheets were part of much larger corpus used to train an LLM such as ...
- 197
2
votes
1
answer
39
views
What is model inferencing - computation or look-up?
I am defining inferencing as querying the LLM. For example, if I goto ChatGPT and enter text in the text box, then I am inferencing the OpenAI LLM (GPT-x). From the UI's perspective, clearly it is an ...
- 197
1
vote
3
answers
127
views
Domain specific content generation - RAG or fine-tune?
I am exploring requirements for a project whose final output is a Markdown file where, the contents of the file are generated by a LLM. The contents will be similar to "Executive Summary" of ...
- 197
4
votes
2
answers
381
views
How do I prevent Gemini from including my IP address location in its responses?
I use Google’s Gemini (formerly known as "Bard") to generate creative works, such as stories. However, I have noticed that Gemini often inserts details from my IP address location into its ...
- 200
0
votes
1
answer
424
views
Ollama Hallucinations for Simple Questions
Recently I installed Ollama and started to test its chatting skills.
Unfortunately, so far, the results were very strange.
Basically, I'm getting too much hallucinations even for simple questions like:...
- 49
4
votes
3
answers
6k
views
Ollama GPU Support
I've just installed Ollama in my system and chatted with it a little.
Unfortunately, the response time is very slow even for lightweight models like tinyllama.
It seems that Ollama is in CPU-only mode ...
- 49
1
vote
1
answer
150
views
Why LLMs are poor when recognizing weekdays for specific dates?
I asked the LLaMA V2 LLM using this site: https://llama2.ai/ - for the respective weekdays for February 29 for leap years since 2000.
Here is the response:
I'm happy to help! Here are the respective ...
anon
-3
votes
1
answer
3k
views
Best realistic story telling LLM?
I've been using WizardLM-SuperCOT30bUncensored for quite some time now, and I'm wondering if there is anything better these days for stories? Because apparently this model is cool, but I can see that ...
- 11
0
votes
2
answers
631
views
How can I format the input text on Google Translate so that the translation doesn't change person names? [closed]
When I have some texts to translate, I notice that sometimes, Google Translate messes up person names. E.g.:
The interview went well. Cherry is good.
becomes:
L'entretien s'est bien passé. La ...
- 2,843