-
@LTH14 In my attempts with causal methods, I have managed to reduce the diffusion loss to 0.3, but the generated images during inference still turn out chaotic. I've noticed that after sampling, the…
-
Thank you very much for your excellent work!
In the file "translate.py" line 128:
```
enc1 = self.encoder('fwd', x=x1, lengths=len1,
langs=langs1, causal=False)…
-
I am having a go at running inference and evaluation for this model, and running into a TypeError in `GPTLMHeadModel`:
```
In [1]: import torch
...: from transformers import AutoTokenizer
…
-
@cloudhead mentioned another approach to ordering sequences:
> @fintohaps: was thinking of something related to the ordering of comments when two of them have arrived at the same time - you mentioned…
-
### Describe the issue
Add Gather's output to model's output will trigger this shape issue (except /model/embed_tokens/Gather node in llama).
I found the first sample in NeelNanda/pile-10k dataset…
-
### System Info
- `transformers` version: 4.34.1
- Platform: Linux-5.15.0-86-generic-x86_64-with-glibc2.31
- Python version: 3.11.5
- Huggingface_hub version: 0.17.3
- Safetensors version: 0.4.0
…
-
When ran InternLM2 inference , it reported errors as below:
oneAPI :2024.0.1.46
ipex-llm: 2.1.0b2
transformers: 4.37.2 ,4.38.2
----------------------------------------------------------------…
-
### System Info
transformers - 4.41.2
peft - 0.11.1
accelerate - 0.31.0
Python - 3.10.14
OS - Ubuntu 20.04.6 LTS
### Who can help?
_No response_
### Information
- [X] The official example s…
-
Your work is very instructive, but the C part of the code can't be debugged.
I want to learn about the function :
causal._causal.sample_mlp(self._np_W0gt, self._np_B0gt,
…
-
**Descriptions:**
Currently, we support a limited intervention use case on stateful models such as GRU. For instance, after the intervention, although the causal effect of the intervening site would …