-
**What**
- We propose supporting the GPTQ algorithm, a state-of-the-art post-training quantization (PTQ) method that has demonstrated robust performance,
effectively compressing weights. Notably, G…
-
https://aclanthology.org/2023.eamt-1.19/
-
Fix the links urls in the MED section (and a few other sections) to pass `check_links` action.
Requirements:
- All links should be formatted in markdown (if possible)
- All URLs should be format…
-
When I call "fit" or "evaluate" on a tfrs.model.Model the loss values (total_loss, loss, and regularization_loss) returned are only based on just the last batch (or last batch of each epoch for "fit")…
-
Hello,
Thank you for your work! I am currently exploring the Spaceship Titanic competition within your Kaggle datasets and noticed a file named `answer.csv` in the env folder. It seems to be associ…
-
Hi! Loving the Arena for quick inspection of models :)
I noticed that the scores for the retrieval are computed as dot products, as opposed to cosine similarity, even though the embeddings are not…
-
### 🚀 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…
-
Hi, I fine-tuned a model (yam-peleg/Experiment26-7B) using unsloth. Then during inference, model correctness drops when using unsloath FastLanguageModel. I see some modules are replaced. It looks a li…
-
Hi, what a fantastic resource for developing intelligent LLM agents!
I wanted to highlight a recent paper presented at ACL 2024 Findings: [TimeChara: Evaluating Point-in-Time Character Hallucinatio…
-
We propose [MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models](https://arxiv.org/pdf/2405.13053). Our proposed MeteoRA (Multiple-Tasks embedded LoRA) is a scalable and efficient framewor…