-
![图片](https://user-images.githubusercontent.com/13312038/202338124-c4ff5c1e-5f54-46ef-8c2b-01923a20ee7b.png)
Hi,getnamo:
I try to use ToBytes(SoundWave) function to convert soundwave to bytes.…
-
In the llm-chatbot notebook - https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb, within the section "Weight Compression using Optimum Inte…
-
### File Name
gemini/getting-started/intro_gemini_1_5_pro.ipynb
### What happened?
The below is mentioned in the notebook for Gemini 1.5 Pro, but unfortunately all examples are for Google Cloud hos…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Using open source LLMs `zephyr-7b-alpha`, how can I do multiple document RAG especially …
GxTeo updated
5 months ago
-
[AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://arxiv.org/pdf/2306.00978.pdf)
The original study compares performance against the number of 'fraction of weigh…
-
### Describe the bug
When I executed code.ipynb, AssertionError happened after waiting for 2-3 mins:
```
from llmlingua import PromptCompressor
import os
os.environ['CUDA_VISIBLE_DEVICES'] = "1…
-
Great work.
I would like to introduce two papers:
Name: Weight-Inherited Distillation for Task-Agnostic BERT Compression
paper:
code: https://github.com/wutaiqiang/WID-NAACL2024
Blog: https:/…
-
### Bug Description
Hello,
I do have strange error, I am using Windows 11 Pro,
And while trying to use Credentials file on VertexAI, I am always getting
'Error Building Component
Error build…
-
Currently we use agents to craft the query, we would either like more standard retrieval strategies that can be added out of the box in our RAG connector (TS, Python, Mongo). Using langchain
Name | …
-
![image](https://github.com/hkust-nlp/llm-compression-intelligence/assets/24559732/0c1e36a4-52e2-49d6-a388-ef0618d1aa2f)
![image](https://github.com/hkust-nlp/llm-compression-intelligence/assets/2455…