-
### Describe the issue
When I fine-tune the llava-1.5-7b using `scripts/v1_5/finetune_lora.sh` with minimal changes, here is my command
Command:
```
deepspeed llava/train/train_mem.py \
--l…
-
Updating taggui to the latest state of the main branch and also making sure that `requirements.txt` are installed I'm now trying to use `THUDM/cogagent-vqa-hf` but I get this message:
```
Loading TH…
-
Hello. I'm trying to run this lib on an Ubuntu OS, using GPU acceleration with an Nvidia 1660 Super.
I was able to run the java-llama.cpp lib with a custom llama.cpp, when I built the llama.cpp lik…
-
Dear Team,
Thank you for sharing this great work with the community.
I am trying to set up the inference model for Video-LLaMA but I am having difficulties in downloading the official LLaMA 7b w…
-
### System Info
- `transformers` version: 4.37.2
- Platform: Linux-3.10.0-1160.108.1.el7.x86_64-x86_64-with-glibc2.27
- Python version: 3.10.13
- Huggingface_hub version: 0.21.3
- Safetensors ver…
-
### Describe the bug
I tried to load the model https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ (the example in model documentation). It fails quitely and without any errors the program just s…
-
I have found a problem with calculating perplexity. Maybe it is model dependent.
https://github.com/EleutherAI/lm-evaluation-harness/blob/7d9922c80114218eaf43975b7655bb48cda84f50/docs/model_guide.m…
-
An error occurs on the line 801 of train_graph.py, that is 'pretrain_graph_model_path' is not defined.
-
Hello, thanks for your great work. I would like to inquire about the datasets used during the finetuning phase of your model. Specifically, I'm interested in knowing if datasets like `COCO`, `GQA`, `O…
-
using this example:
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_path = 'lmsys/vicuna-7b-v1.5'
quant_path = 'vicuna-7b-v1.5-awq'
quant_config = { "zero_poin…