-
### Have you completed your first issue?
- [X] I have completed my first issue
### Guidelines
- [X] I have read the guidelines
- [ ] I have the link to my latest merged PR
### Latest Merged PR Lin…
-
## Description
Make a RAG Chatbot for tibetan text with vectorization.
## Important Notes
- prompt can be both in english or tibetan
- answer should be given in tibetan
- vectorization would be used…
-
It would seem that after the install when asked to add a task bar short cut and I answered n, it said that it added it despite the fact that it did not, this is most likely a small error in the text f…
-
I'd like to be able to set the system prompt from the call to `ollama` in my shell, rather than in the conversation. For example:
```sh
ollama run llama3.1 --system="Your nickname is 'Grass' now"
…
-
Hello!
I'd like to request a way for the player to enter free-text during a dialog, which can then be used in executing commands, or future dialogs. I'm thinking of saving the input as a custom pla…
-
When performing quick and short searches, the WebSearchShortcut extension functions correctly. However, when typing longer prompts, such as those intended for the Perplexity.ai website, the text input…
-
Hi! I'm trying to edit the PS1 initial value so that it doesn't always output my long username in the prompt, but it seems that oh-my-bash ignores this and always has the same prompt text. What's the …
-
I'm running the tutorial [vllm/offline_inference_with_prefix.py](https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_with_prefix.py) and measuring the generation times, again bel…
-
We could call tokenizer, or ask litellm to support pre-check before api call (this will be better)
-
Trying to run following gpt2 demo with triton-cpu and certain tirton kernel fails with above error:
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from torch._…