-
Hi,
I recently fine-tuned the phi-3.5-moe-instruct model and phi-3.5-mini-instruct model using PEFT LORA. It seems the Moe model is performing way worse than 3.5 Mini Are there any specific things …
-
Following local finetuning README
Ran `python gradio_chat.py --baseonly`
Got:
```
(phi-3-env) hayden@XPS15:/mnt/d/phi-3-env/inference$ python gradio_chat.py --baseonly
Number of GPUs availa…
-
After commit 47d831f2c90225a7d2 (https://github.com/llvm/llvm-project/pull/100514) I noticed a regression in a downstream benchmark, due to a loop no longer being vectorized. It seems like the changed…
bjope updated
3 weeks ago
-
Hi there,
Thanks for your great work! I am wondering what optimization strategy is used for finetuning the model. Since the gradient checkpointing is NOT implemented by modeling_phi.py, finetuni…
-
The example output file is attached.
to produce such output:
./build/calc -y -pn pi+ -i input/beta.dat -o output/y_test_for_nils.dat
dN/dy = int pTdpT dphi_p dNd3p
dN/pTdpT = int dy dphi_p d…
-
I am running the phi-2 on iOS using the code from LLMEval.
I have ported over an implementation of the CodeGen Tokenizer into swift as a standalone file:
```swift
import Foundation
struct BP…
-
### Details
1. It seems that `out_mat_dh` calculates only the Pulay term $\braket{\phi|H|d\phi}$ while the Hellmann-Feynman term $\braket{\phi|dH|\phi}$ is missing? (see the implementation in `spar…
-
VAR is indeed impressive, but there’s one issue that’s been bothering me. We reached out to the authors for assistance with the matter, and we appreciate your help.
In the quant.py line 33: self.qu…
-
### bug描述 Describe the Bug
您好,在使用`paddle.index_fill_`时,似乎存在以下问题:
当`paddle.index_fill_`输入的`index`为2-D, 3-D的Tensor时,出现Aborted (core dumped)或Segmentation fault (core dumped)。
同时可能出现munmap_chunk():…
-
Hi,
trying to run the differential_equation_tutorial.py example on WSL (Ubuntu 20.04). I run into this error:
```
f: [-x0+sin(x0)]
Traceback (most recent call last):
File "", line 1, in
…