-
Hi,
I'm trying to apply context-debias to generative models (gpt2). I tried to directly use your script but the loss is extremely large (1e10+). I notice you have an argument "mlm" in run_debias_mlm…
-
- [ ] Use the attention module in modalities.nn in GPT2
-
```console
$ GPU=1 python examples/gpt2.py --model_size=gpt2
using GPU backend
using gpt2
ram used: 0.50 GB, lm_head.weight : 100%|█████████████████████████████…
-
**Tasks:**
pytorch/pytorch#116949
**Documentation:**
[torch.export](https://pytorch.org/docs/stable/export.html)
**Examples:**
[exported_program.pt2.zip](https://github.com/lutzroeder/netron/files/1…
-
ran through the tutorial using the simple_openai.yaml and it worked. I am trying to use the full.yaml and I am getting the following error
`bm25_path .\resources\bm25_gpt2.pkl does not exist. Pleas…
-
Running model forwards within a process seems to get stuck. I tried to set `TOKENIZERS_PARALLELISM` to `true` and `false` but unfortunately both couldn't help 🥲
### System Info
`transformers-cli…
-
part 2 intro to merch interp, [this block doesn't run](https://github.com/callummcdougall/ARENA_3.0/blob/main/chapter1_transformer_interp/exercises/part2_intro_to_mech_interp/solutions.py#L181):
```p…
-
I get this error when trying to convert `gpt2`
```
/site-packages/coremltools/converters/mil/mil/input_type.py", line 162, in validate_inputs
raise ValueError(msg.format(name, var.name, input…
-
Hi, I am trying out this great framework with a self trained GPT-2.
I wanted to use a custom trained model and the base model as tokenizer.
No matter if I use this approach or solely the base mo…
-
python -m garak --model_type huggingface --model_name gpt2 --probes lmrc.Profanity
garak LLM vulnerability scanner v0.9.0.14 ( https://github.com/leondz/garak ) at 2024-08-13T10:51:03.868133
🦜 loadi…