-
# Description
I write a inference script like this:
```python
import torch
from PIL import Image
import sys
sys.path.append('./')
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAG…
-
### System Info
I am using a Tesla T4 16 gb
### Reproduction
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
base_model_id = "mistralai/Mistral-7B-…
-
### ❓ The question
Hi, I am wondering if you can provide your config file for finetuning on the Tulu V2 dataset? It would be helpful for reproducing the finetuning results. In addition, have you tr…
-
Hi @danielhanchen
I try out to do FT with a different model like Nous Research LLAMA31 8B Instruct
I get an Error.
Is it really needed to make those other target modules trainable?
I want to tra…
-
Does this tage_2 checkpoint weights your provide include Qformer part weights which PEFT from data {alpaca_gpt4_data.json and lava_instruct_150k.json } ?
https://huggingface.co/Alpha-VLLM/LLaMA2-A…
-
Hi, thanks for your great repo.
I am trying to use this code to fune-tune llama2-7b on tulu-v2. And I find we always get the same loss curve when I use different seed. I guess this is because the d…
-
When training either Llama 3 or 3.1 8B base model using the Llama 3 template for conversation prompt format, it seems to not train with the correct tokens. It ends up producing text containing tokens…
-
when load the optimizer.pt display the key is different
KeyError: 'base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight'
the items in optimizer.pt state is 0~255.
-
I notice that operating truthfulqa.sh requires "gpt_true_model_name" and "gpt_info_model_name". But it seems the original model is unavailable now.
-
Dear VideoLLaMA2 Maintainers,
I have been using your library and successfully fine-tuned models with LoRA and QLoRA on my own dataset. However, I noticed that the repository does not include code f…