-
I tried to run bfloat16 linear of bitblas
but I got different result
output:
qunatizing /decoder/block/0/layer/0/SelfAttention/k
torch linear took by avg 7.802581787109375e-05
BitBLAS Op…
-
We need unit tests for the linear models which compute the base risk factors in `static_linear_model.cpp` - i.e. `initialise_factors` and `update_factors`.
These should check:
- [ ] are residuals com…
-
### Description of the bug:
I am working on making my model to be GPU-compatible on TFLite, and one of the issues to solve is to bypass some operators that do not support broadcasting on GPU. One…
-
I tried to linearize a simple electrical system and received an error message when using option ```analytic=true```
* ```linearize!(model, analytic=false, ...``` ==> OK
* ```simulate!(...``` ==…
-
### Describe the workflow you want to enable
I want to be able to use multiple estimators in one pipeline. E.g.
```python
from sklearn.pipeline import Pipeline
from sklearn.linear_model impor…
-
Hi dear authors,
I am on a Mac with 64GB of RAM, I am trying to run the encoding model with the following code
```
results_df_clip = Linear_Encoding(
feat_path=feat_path,
roi_path=roi…
-
Running this command
```
CUDA_VISIBLE_DEVICES=0 python3 model/llama.py ShiftAddLLM/Llama-2-70b-wbits2-acc
```
I'm seeing this error
```
CUDA extension not installed.
Loading checkpoin…
-
OS: Linux Ubuntu 22.04
MZN version: 2.8.5
Hello! I am currently working on a MiniZinc model involving float and integer variables, using a linear solver (in my case, SCIP 8.0.4). In the model, I h…
-
I'm getting a couple of dtype-related errors when using the MLP module in a torch.autocast block. Here's my simple wrapper of the MLP module:
```py
from scattermoe.mlp import MLP as MoE
class…
-
When merging models with different structures in linear, the following error occurred
I understand that errors can occur, but is there a way to skip specific layers where the error occurs?
```
Trac…