-
No sound comes out of my browser when I set tts by alltalk in kobold.
It's related to #920, however, in alltalk v2 nothing is fixed. Same thing happens when I start v1 or v2. It's no different. Wha…
-
```
import os
from langchain_core.prompts import PromptTemplate, FewShotPromptTemplate
from langchain_experimental.synthetic_data import create_data_generation_chain
from langchain_experimental.…
-
Hi,
Thank you for your valuable contribution and impressive project. I evaluated the ``llama-2-chat'' model on the TriviaQA task and obtained very low performance:
| Tasks |Version| Filter …
-
Multilingual Amazon Reviews Corpus ([MARC](https://paperswithcode.com/dataset/marc)) {En, Jp, De, Fr, Es, Zh} [2015 2019] text classification: review text, the review title, the star rating, an anonym…
-
## DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
### Summary by Copilot
- **DIN-SQL** stands for **Decomposed In-Context Learning of Text-to-SQL with Self-Correctio…
-
I would like to raise the issue of configurable tab stops.
A proposal has been floating around the web for a few years, called [Elastic tabstops](http://nickgravgaard.com/elastictabstops/), that prom…
tobia updated
4 years ago
-
### Ticket Contents
1. **Create JSON schemas that capture the details of the sample court docs**
The goal is to consolidate all the important data points from the documents and create an exhaustiv…
-
Part of the appeal of today's distributed content generation is the ability not to have to separately maintain metadata/datasets - when they are better maintained elsewhere by others. It's safe to ass…
-
I modified the codebase a little:
```
"""code for zero shot instruction parsing"""
import torch
from peft import PeftModel
import transformers
import textwrap
from transformers import AutoMod…
-
CoT currently consists of GSM8K, MATH, BBH & MMLU. The first three things are fine and it has been shown that CoT gives significant improvements for these benchmarks.
However, the same is not true …