-
As it seems now. There is no non-linearity in the neuron model applied. This might be the reason of the poor complex model performance.
-
`#find query FFN neurons activating attn neurons
curfile_ffn_score_dict = {}
for l_h_n_p, increase_score in cur_file_attn_neuron_list_sort[:30]:
attn_layer, attn_head, attn_neuron, attn_pos = l…
-
### Summary
Currently, the [linear model](https://docs.deepmodeling.com/projects/deepmd/en/master/model/linear.html) is implemented to combine multiple frozen models. However, this architecture can b…
-
Fails for both `Mistral-7B-Instruct-v0.2` and `intfloat/e5-mistral-7b-instruct `
Only fails with `tp_degree=1`, good for `2
-
**server:** inf2.8xlarge
**vllm version**: 0.6.3.post2.dev77+g2394962d.neuron215
_Desctiption_
Hellow! I am trying to run the code below (the code was taken [here](https://docs.vllm.ai/en/v0.4.1/…
-
### System Info
```shell
accelerate 1.1.1
neuronx-cc 2.14.227.0+2d4f85be
neuronx-distributed 0.8.0
neuronx-distributed-training 1.0.0
optimum …
-
Hi,
I am trying to `llama3.2 1B` fine-tuning using AWS Trn1 and I'm running into the following error.
Error in eager mode (without jax.jit):
```
2024-11-21 04:44:13.000699: 3926 ERROR ||NEU…
-
### System Info
```shell
using Huggingface AMI from AWS marketplace with Ubuntu 22.04
optimum-neuron 0.0.25
transformers 4.45.2
peft 0.13.0
trl 0.11.4
accelerate 0.29.2
torch 2.1.2
```
…
-
Hi, I tried a test about compiling unet(torch.float16), which is the part of StableDiffusionXLPipeline in Inferentia2.8xlarge and it failed.
When the latent size of unet is (64, 64), it did not fai…
-
### Feature request
I just wonder is it possible to use ip-adpater with optiumum-neuron environment.
Because I found ip-adapter related parameter in [pipeline](https://github.com/huggingface/opt…