-
[mlir file](https://storage.googleapis.com/shark_tank/vicuna/unsharded/mlir/second_vicuna_fp16.mlir)
benchmark command:
`TRACY_NO_EXIT=1 sudo ../iree-build/tools/iree-benchmark-module --module=/ho…
-
## TODO Templates
- [x] Athene V2 (36e9ae2877beefca51101176202761f34bce0b8e)
- [x] ChatML (ccd461ac30c116110a7adda507ce56596fefb1ca)
- [x] LLaMa2 (9be35a3c689dde0dfce0f497d83c7e5c3b606dc3)
- [x] L…
-
this code is for vicuna-7b-delta-v1.1, then which code is for vicuna-7b-delta-v0?
and …
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior:
Please use:
2 node(s), each with 8 G…
-
Hi, thank you for your wonderful work!
I've tried to run "finetune_toy.sh" following this:
# prepare toy data and pretrained models
./prep_train.sh
# run finetuning on the data
./finetune_t…
-
Hello, I wonder why adding special tokens in [blip2_vicuna_instruct.py](https://github.com/salesforce/LAVIS/blob/main/lavis/models/blip2_models/blip2_vicuna_instruct.py#L86-L89)?
```
self.llm_tokeni…
-
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_i…
-
Dear Eagle Team:
Hello, and thank you very much for your excellent work for the community. Recently, while attempting to replicate Eagle, I encountered some issues that I have been unable to resolv…
-
### Already reported ? *
- [X] I have searched the existing open and closed issues.
### Regression?
Yes
### System Info and Version
System/Version info
```sh
Hyprland 0.45.0 built from branc…
-
Hi, I changed the llm_model's path to "Salesforce/instructblip-vicuna-7b" in the file blip2_instruct_vicuna7b.yaml, and then I fellow the instruction to run the code: `model.generate({"image": image, …