-
### Feature request
Support Musicgen Melody's ONNX exportation with audio prompting.
### Motivation
Currently, Optimum do not support export for Musicgen Melody models, The current implementation i…
-
Thank you for sharing the code!
Could you please let me know which versions of **_Triton, Torch, Casual-conv1d, and Mamba-ssm_** you are using? I encountered some wired issues with mamba and casual…
-
Used the following lines for env creation
****
conda create --name unsloth_env python=3.10
conda activate unsloth_env
conda install pytorch-cuda= pytorch cudatoolkit xformers -c pytorch -c nvi…
-
### Motivation.
As vllm supports more and more models and functions, they require different attention, scheduler, executor, and input output processor. . These modules are becoming increasingly com…
-
It would be convenient to allow the encoder [output_size](https://github.com/CUNY-CL/yoyodyne/blob/master/yoyodyne/models/modules/lstm.py#L99) to be different from the TransformerDecoder embedding siz…
-
When using ORPO to fine-tune mistral-7b-instruct-v0.3-bnb-4bit, after clicking orpo_trainer.train() to start, the following error message appears:
`-------------------------------------------------…
-
```
{
"name": "CompilationError",
"message": "at 53:4:
loss_ptr += row_idx
logsumexp_ptr += row_idx * N_CHUNKS + chunk_idx
labels_ptr += row_idx
col_offsets = chun…
-
Hi Vik,
Thanks for all the help! And it works perfectly with `cuda` option. Wondering if you have seen this before while using `cpu`
The model is loaded by:
```
DEVICE = "cpu"
DTYPE = torch.f…
-
### 🐛 Describe the bug
``` Python
from functools import lru_cache
from torch.nn.attention.flex_attention import flex_attention, create_block_mask
import torch
torch._dynamo.config.cache_s…
-
### Question
Hello,
I have trained a LlavaMistralForCausalLM model based on openchat (**not moe version**), but when I use predict.py
I get the following error:
```
File ~/scripts/MoE-LLaVA/…