-
I propose adding a Model Evaluation and Benchmarking System to ML Nexus to help users assess their model performance on standardized datasets and compare it against benchmarked scores. This feature wo…
-
Now the custom import model is GAed, we need to evaluate the cost performance using FMBench with customized model arn.
-
Hello, excellent work! I have a question regarding the reproducibility issue for GNN models. When using PyG to construct these models, the performance may experience significant shifts even when using…
-
Own ollama server is working on single llm model without unloading.
Running comfyui-ollama with keep_alive will cause server to unload a model every time.
We need ability to skip this loads/unloads …
-
This feature aims to enhance the current genome encoding model by integrating an **autoencoder** to compress and encode neural network weights into a latent vector. The autoencoder will replace the di…
-
- [ ] Implement a webhook to auto-load new models, but compare performance before deploying to prod.
- [x] Connect MLflow with DagsHub.
- [x] Track experiments using MLflow.
- [x] Exp-1 Baseline Model…
-
With less than 5 finetuned checkpoints, how could `Uniform Average` perform almost the same as `Model Stock…
-
### Proposal to improve performance
Improve bitsandbytes quantization inference speed
### Report of performance regression
I'm testing llama-3.2-1b on a toy dataset. For offline inference using the…
-
Almost all functions require a call to `merge_pars` because low-level functions are only implemented for the most general cases.
For polytomous models the `deepcopy` call in `merge_pars` requires …
p-gw updated
4 months ago
-
### Description
We aim to enhance our speech-to-text (STT) model by fine-tuning it using exclusive speaker-specific data combined with our existing base training data. We will use Low-Rank Adaptation…