-
The project aims to fine-tune the Llama 2 7B, a high-resource language model, using lecture data, and compare its performance with a mini Language Model (LLM) trained on the same dataset. The comparis…
-
I'm wondering if I can get an easier pipeline by loading the awq weights with vllm:
```
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the Uni…
-
### Problem
The CLI needs a new RPC method that allows for code changes to be applied to a specific file. This method should take in a file path and new code content, and then use the language model …
-
- [ ] [DeepSeek-V2: A Strong, Economical, and Efficient MoE LLM of 236B total parameters](https://github.com/deepseek-ai/DeepSeek-V2)
# DeepSeek-V2: A Strong, Economical, and Efficient MoE LLM of 2…
-
This was my first time working with LLMs as a Machine Learning Engineer. So, I've learned a few things:
- Prompt engineering is very crucial for the performance and accuracy of the application and ev…
-
### Problem Description
For now, it's hard to switch between LLM providers. Every time I have to switch from one LLM provider to another, I need to get the API key and copy/paste manually, then put t…
-
Referencias:
- [ReLeLa](https://relela.com/)
- [BETO: Spanish BERT](https://github.com/dccuchile/beto)
- Los modelos de [Jorge Ortiz Fuentes](https://huggingface.co/jorgeortizfuentes) como [Tulio…
-
Layer-Condensed KV Cache for Efficient Inference of Large Language Models
https://arxiv.org/abs/2405.10637
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
https://tr…
-
### 🚀 The feature, motivation and pitch
https://arxiv.org/pdf/2403.11421.pdf
This paper might be interesting.
> Cost of serving large language models (LLM) is high, but the
expensive and scarc…
-
### Question
Nvidia GPUs are energy thirsty chips. If Nvidia Stock will indeed Reach $10 Trillion Market Cap By 2030, how would it impact the environment? This is potentially unsustainable, and curr…