3
votes
Accepted
How are characters created in Character.AI and similar services?
While I'm not too versed with Character.ai, I can explain a bit about "similar services" which use the Character Card V2 specification. I suspect C.ai works in the same way, but a confirm/...
- 196
2
votes
Accepted
How much RAM is required for model inferencing?
GGUF = new file format aiming at replacing GGML.
Yes.
(V)RAM requirement for inference: Model size < RAM requirements < Model size * 1.2.
https://huggingface.co/spaces/hf-accelerate/model-...
- 4,181
2
votes
Is there any AI apis that can remember your information?
there are a few ways to handle the conversational history, but one mainstream method is that you as the application developer handle this. for example, you send to the LLM api the following (the part ...
- 121
1
vote
To what extent can GenAI be used for content moderation?
Fine-tuning pretrained foundation models
Large language models such as GPT-4 or Llama-2 are trained on the task of generating the next token in a sequence, but can then be fine-tuned (or perform zero-...
- 2,099
1
vote
Accepted
What is model inferencing - computation or look-up?
Yes. 3. Stateless between two subsequent inferences. 4. Add or remove model instances eg via Kubernetes depending on API usage.
- 4,181
1
vote
Is there any AI apis that can remember your information?
I want to augment to @NirO.'s answer. Yes, it is theoretically possible to recall the user's identity from the chat-history. But there are some practical issues here like:
When the chat becomes too ...
- 171
Only top scored, non community-wiki answers of a minimum length are eligible